Showing 1–50 of 164 results for author: Han, F

Decomposing Staleness in Recommender Systems: A Dual-Filter Framework for Supersession and Decay

Authors: Di Bai, Feng Han, Zhenwei Tang, Jintao Liu, Luoshu Wang, Jialu Liu

Abstract: Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms. Items lose relevance through two primary mechanisms: supersession, where emerging updates render prior coverage stale, and relevance decay, where an item's informational value naturally diminishes over its lifecycle. Traditional countermeasures serve as crude proxies: age cutof… ▽ More Stale recommendations are a pervasive challenge and a leading source of user complaints on large-scale content platforms. Items lose relevance through two primary mechanisms: supersession, where emerging updates render prior coverage stale, and relevance decay, where an item's informational value naturally diminishes over its lifecycle. Traditional countermeasures serve as crude proxies: age cutoffs poorly reflect actual relevance loss, while engagement heuristics rely on lagging signals, broadly exposing users to stale content before the system adapts. We present SDF (Supersession-Decay Filtering), a staleness filtering system fully deployed in Google Discover, a personalized recommendation feed with hundreds of millions of daily and billions of monthly active users. SDF targets both mechanisms with complementary filters, each powered by a learned model: a relational staleness model that detects supersession between item pairs, and a predicted traffic ratio (PTR) model that forecasts relevance decay from the item's content, trained on lifetime visit traffic. Applied via disjunction upstream of the ranking stage, SDF prunes stale candidates, measurably reducing downstream serving costs. Online experiments demonstrate that these filters significantly reduce the prevalence of stale content while improving user engagement. Over a two-year production deployment, user-filed staleness reports (in-product user feedback) declined by 54.9% relative to the pre-deployment baseline, establishing SDF as a robust and scalable paradigm for resolving content staleness at industrial scale. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Comments: CIKM Applied Research Track 2026

An improved bond-associated peridynamic model and its adaptive coupling with CCM for fracture analysis

Authors: Wenping Han, Bowen Sun, Shankun Liu, Fei Han

Abstract: This paper reformulates the correction factor in the force-state of the bond-associated peridynamic (BAPD) model. The reformulation is established from the strain energy density equivalence between the BAPD model and the classical continuum mechanics (CCM) model at a material point. With the FEM solution taken as the reference, the proposed correction factor improves the accuracy of the BAPD solut… ▽ More This paper reformulates the correction factor in the force-state of the bond-associated peridynamic (BAPD) model. The reformulation is established from the strain energy density equivalence between the BAPD model and the classical continuum mechanics (CCM) model at a material point. With the FEM solution taken as the reference, the proposed correction factor improves the accuracy of the BAPD solution in this study. Furthermore, a BAPD-CCM coupled model is developed based on the above energy density equivalence, and a ``Morphing" function is introduced to achieve a smooth transition between the two models. For time integration, explicit schemes are adopted for both quasi-static and dynamic problems. In the spatial discretization, the CCM model is discretized by elements, whereas the BAPD model is discretized by particles. The solution accuracy of the coupled model is validated by comparison with the FEM solution and by evaluating the $L^{2}$ norm, the $H^{1}_{\mathrm{semi}}$, and the energy norm of the displacement error. Two- and three-dimensional numerical examples show that the proposed model has higher computational efficiency. For example, in the Mode I crack propagation problem, its computational cost is reduced by more than 72\% compared with that of the pure BAPD model, and the predicted crack patterns agree with experimental results. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Long SKILL Compliance as Logical Reasoning: Closure-Grounded Detection with Scaling-Guided On-Policy Distillation

Authors: Shuaitao Zhao, Feng Ni, Lichao Ma, Jiaye Lin, Fei Han, Yang Wei, Lu Pan

Abstract: The increasing complexity of enterprise business scenarios has promoted the widespread adoption of long SKILL documents in agent systems, posing new challenges for compliance detection: large models incur substantial inference costs, while small models may fail to maintain detection accuracy. To address this gap, we propose SkillCDG, a graph-based framework for long SKILL compliance detection. Ski… ▽ More The increasing complexity of enterprise business scenarios has promoted the widespread adoption of long SKILL documents in agent systems, posing new challenges for compliance detection: large models incur substantial inference costs, while small models may fail to maintain detection accuracy. To address this gap, we propose SkillCDG, a graph-based framework for long SKILL compliance detection. SkillCDG represents complex business policies as a two-layer constraint dependency graph, where the upper layer indexes SKILL descriptions for scenario routing and the lower layer captures dependencies among atomic constraints within each SKILL. During inference, two-level retrieval followed by dependency closure supports compliance judgment and source traceability. We comprehensively evaluate the framework on three enterprise datasets and two controlled public benchmark variants. Experimental results demonstrate that SkillCDG outperforms baseline methods by up to 12.8 percentage points in detection F1 score, while reducing token consumption by a maximum 64.3\%. Moreover, we further investigate the inherent relationships among policy-graph complexity, model scale, and detection performance. Comparative experiments conducted on four checkpoints from a single model family validate a concise and effective scaling trend: end-to-end detection correctness exhibits a complexity-differentiated scaling pattern, and the complexity metric derived from the constraint dependency graph can effectively quantify instance difficulty and the performance improvement potential of models. Leveraging this insightful scaling trend, we conduct adaptive training sample selection and adopt on-policy distillation to efficiently enhance the compliance detection capability of small-scale models. △ Less

Submitted 8 August, 2026; originally announced August 2026.

DiffImaginE: Imagine to Verify Entity Types with Diffusion

Authors: Feng Zhang, Feiyu Han, Rongxin Yang, Yang Liu, Yancheng Chen, Rui Wang, Yingguang Yang, Tian Xueyun, Chongyang Zhang, Hao Zheng, Xu Kefu, Congjing Ran, Fuhai Chen, Bin Chong

Abstract: Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual evidence. Existing imagine-and-compare verifiers map each (span, type) pair to one predicted visual feature, compressing diverse visual realisations into a single prototype and providing a compatibility score without explicit probabilistic semantics.… ▽ More Multimodal named entity recognition (MNER) determines whether each candidate span and entity-type hypothesis is supported by joint textual and visual evidence. Existing imagine-and-compare verifiers map each (span, type) pair to one predicted visual feature, compressing diverse visual realisations into a single prototype and providing a compatibility score without explicit probabilistic semantics. We introduce DiffImaginE, which formulates MNER type verification as conditional latent diffusion inference. Given span-localised visual evidence, a type-conditioned denoiser predicts noise injected into its standardised latent. The resulting denoising error provides an ELBO-consistent surrogate for type-conditional negative log-likelihood, allowing competing type hypotheses to be ranked by how well they explain the observation. DiffImaginE retains a standard multimodal encoder stack and replaces the deterministic verifier with a classifier-free-guided diffusion scorer trained using Min-SNR weighting. We directly supervise per-type diffusion scores as classification logits, learn aggregation across noise levels, and use antithetic sampling to reduce Monte Carlo comparison variance. Our analysis shows that classifier-free guidance sharpens the induced type posterior and characterises when antithetic pairing reduces variance at equal denoiser cost. Experiments on Twitter-2015 and Twitter-2017 show consistent gains over a matched deterministic ImaginE control under the same encoder, auxiliary objectives, and evaluation protocol, supported by ablations and paired significance tests. △ Less

Submitted 16 August, 2026; v1 submitted 3 August, 2026; originally announced August 2026.

SlimPer: Make Personalization Model Slim and Smart

Authors: Siqi Wang, Xianjie Chen, Shaofeng Deng, Albert Chen, Romil Shah, Jiawei Huang, Zhaoqin Wang, Zhang Zhang, Yiqun Liu, Meilei Jiang, Anish Dubey, Moyan Mei, Tongxin Wang, Nathan Berrebbi, Misael Manjarres, Armand Sauzay, Shardul Kothapalli, Aryaman Vinchhi, Kevin Johnstone, Juheon Lee, Gufan Yin, Ziheng Huang, Justin Lin, Mert Terzihan, Yilin Qi , et al. (20 additional authors not shown)

Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each <user,… ▽ More Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet they inherit a design premise misaligned with the task: generative models rely on per-token autoregressive prediction, which justifies maintaining large intermediate tensors that scale with sequence length. In contrast, recommendation systems produce a single set of relevance scores for each <user, item> pair without token-level supervision. Leveraging this observation, we propose SlimPer, which reformulates personalized ranking as iterative refinement of a compact, unified <user, item> knowledge base. At each layer, the model selectively queries raw multi-modal user-side tokens, computes explicit relevance matching scores, and refines the knowledge base, all in O(N) per-layer cost with a fixed-size intermediate representation. As a result, model depth is decoupled from user history length, enabling deeper relevance understanding without proportional growth in compute or memory; request-only optimization further trims memory by sharing a single copy of user-side tokens across all candidate items. SlimPer unifies sparse, dense, and sequence features within a single backbone and provides inherent interpretability through its attention mechanism. Deployed on Instagram Reels and Feed, SlimPer yields measurable improvements in user engagement while streamlining the overall system and enabling effective modeling of 10k+ fine-grained user history events. △ Less

Submitted 13 July, 2026; originally announced July 2026.

ICA Lens: Interpreting Language Models Without Training Another Dictionary

Authors: Sida Liu, Feijiang Han

Abstract: Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard tool for this purpose, but using them as the default first lens often requires training, storing, and evaluating large overcomplete dictionaries. This bottleneck limits rapid exploration and raises a fundamental questio… ▽ More Finding interpretable directions in language-model representations is critical for understanding and controlling model behavior. Sparse autoencoders (SAEs) have become the standard tool for this purpose, but using them as the default first lens often requires training, storing, and evaluating large overcomplete dictionaries. This bottleneck limits rapid exploration and raises a fundamental question: how much interpretable structure is already visible from activation geometry before training another neural dictionary? Our intuition is simple: many interpretable directions are selective on tokens, and these directions should look less Gaussian than random directions. We therefore revisit independent component analysis (ICA), a classical method for finding non-Gaussian directions, as a compact lens for language-model interpretability. We find that ICA has been underestimated for LLM interpretability, because prior uses often relied on off-the-shelf ICA implementations that are brittle on LLM activations and lacked systematic tools for inspecting and evaluating the recovered directions. To bridge these gaps, we introduce ICALens, the first practical workflow for stable, efficient, and auditable ICA analysis of LLM representations. It combines an optimized GPU-parallel FastICA pipeline with LLM-specific stability recipes and better fitting diagnostics, enabling efficient and reliable layer-wise analysis. Across GPT-2 Small, Gemma 2 2B, and Qwen 3.5 2B Base, ICALens efficiently recovers compact, human-interpretable directions without per-layer gradient-based dictionary training. On SAEBench, ICA is competitive with public SAEs in sparse probing and outperforms them in targeted probe perturbation under small-to-medium budgets. These results suggest that ICA should not be viewed as a weak baseline, but as an efficient and complementary first lens for exploring language-model representations. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Comments: Ongoing Project

Kwai Keye-VL-2.0 Technical Report

Authors: Kwai Keye Team, Bin Wen, Changyi Liu, Chengru Song, Chongling Rao, Guowang Zhang, Han Li, Haonan Fan, Hengrui Ju, Jiankang Chen, Jiapeng Chen, Jiawei Yuan, Kaixuan Yang, Kaiyu Jiang, Kun Gai, Lingzhi Zhou, Na Nie, Sen Na, Tianke Zhang, Tingting Gao, Xuanyu Zheng, Yulong Chen, Fan Yang, Haixuan Gao, Lele Yang , et al. (28 additional authors not shown)

Abstract: We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based mu… ▽ More We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To address the challenges of ultra-long contexts, information redundancy, and prohibitive computational costs inherent in hour-level videos, Keye-VL-2.0 is the first to adapt DeepSeek Sparse Attention (DSA) to GQA-based multimodal architectures, enabling lossless 256K context processing while capturing critical frames and long-range temporal dependencies. This architecture is underpinned by a highly optimized training and inference infrastructure, including scalable video I/O, heterogeneous ViT-LM parallelism, and custom DSA kernels that significantly maximize throughput and minimize computational overhead. Furthermore, to overcome the algorithmic dilemma of catastrophic forgetting during multi-task alignment, we introduce Cross-Modal Multi-Teacher On-Policy Distillation (MOPD) paired with Context-RL and Video-RL. By distilling dense token-level teacher feedback from on-policy rollouts back into the MoE backbone, which activates only 3B parameters, Keye-VL-2.0 natively empowers advanced agent collaboration across Code, Tool, and Search scenarios with multimodal self-correction. Extensive evaluations across video understanding, temporal grounding, reasoning, STEM, and agent benchmarks demonstrate that Keye-VL-2.0-30B-A3B achieves state-of-the-art performance among models of similar scale, particularly excelling in fine-grained temporal localization on TimeLens and long-video comprehension on Video-MME-v2 and LongVideoBench. We release our model checkpoints to accelerate community progress toward scalable and robust multimodal agentic applications. △ Less

Submitted 9 June, 2026; originally announced June 2026.

Comments: 31 pages, 11 figures

DiBS: Diffusion-Informed Branch Selection

Authors: Bo Liu, Yuan Xie, Yuan Gao, Xiaolong Luo, Peng Ye, Tao Chen, Fujun Han

Abstract: Sudoku is a representative constraint satisfaction problem that requires global structural reasoning under strict discrete constraints. The existing works of solving Sudoku mainly focus on two dominant approaches, i.e., traditional heuristic and deep learning solver. However, they suffer from two complementary limitations: learning-based solvers lack hard correctness guarantees, while complete sym… ▽ More Sudoku is a representative constraint satisfaction problem that requires global structural reasoning under strict discrete constraints. The existing works of solving Sudoku mainly focus on two dominant approaches, i.e., traditional heuristic and deep learning solver. However, they suffer from two complementary limitations: learning-based solvers lack hard correctness guarantees, while complete symbolic solvers are still prone to long-tail search. To address these shortcomings, we propose a novel diffusion model-guided approach, termed as DiBS, for the branch selection search process. Specifically, DiBS keeps the symbolic solver complete and uses the diffusion model as a branch-ordering guide. The core method is ranking candidate values under the current partial assignment and lightweight consistency signal. Furthermore, we provide an in-depth theoretical proof to reveal how it works and why it works. Experiments on the challenging Royle 17-clue Sudoku benchmark show that our DiBS substantially reduces search cost relative to strong heuristic baselines, especially in nodes, backtracks, and long-tail percentiles. Besides, these results confirm that learned global guidance is effective on hard instances where branch-order mistakes are most expensive. All codes are available at https://github.com/shanxierdan/DiBS. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Comments: 12 pages, 6 figures, 3 tables

AutoIQ: An Ensemble Framework for Automatic Assessment of Geometric Distortion in Prostate Diffusion-Weighted Imaging

Authors: Haoran Sun, Lixia Wang, Yin-Chen Hsu, Hsu-Lei Lee, Chang Gao, Fei Han, Robert Grimm, Vibhas Deshpande, Ziyang Long, Hsin-Jung Yang, Rola Saouaf, Alessandro D'Agnolo, Timothy Daskivich, Hyung Kim, Debiao Li, Yibin Xie

Abstract: Geometric distortion in prostate diffusion-weighted imaging (DWI) can impair lesion localization and reduce the reliability of MRI-based clinical assessment. We propose AutoIQ, an ensemble machine learning framework for automatic quantification and classification of DWI geometric distortion severity. A total of 140 retrospective prostate biparametric MRI examinations were analyzed, including 33 sc… ▽ More Geometric distortion in prostate diffusion-weighted imaging (DWI) can impair lesion localization and reduce the reliability of MRI-based clinical assessment. We propose AutoIQ, an ensemble machine learning framework for automatic quantification and classification of DWI geometric distortion severity. A total of 140 retrospective prostate biparametric MRI examinations were analyzed, including 33 scans with severe distortion requiring repeat acquisition and 107 scans with acceptable distortion based on expert radiologist assessment. AutoIQ combines two complementary distortion quantification strategies: a segmentation-based method measuring prostate boundary mismatch between T2-weighted imaging (T2WI) and DWI, and a registration-based method estimating deformation magnitude after DWI-to-T2WI alignment. The resulting distortion scores were used to train individual classifiers and a logistic-regression ensemble model. Both computational methods significantly differentiated severe from acceptable distortion cases (p < 0.001). On an independent test set, the ensemble model achieved an accuracy of 0.95, F1-score of 0.93, and AUC of 0.98, outperforming individual models. These results suggest that AutoIQ can provide automated, quantitative quality assessment for prostate DWI and may help identify scans that require repeat acquisition. △ Less

Submitted 29 May, 2026; originally announced June 2026.

Comments: Original research; 11 pages, 7 figures, 1 table

LoMo: Local Modality Substitution for Deeper Vision-Language Fusion

Authors: Feng Han, Zhixiong Zhang, Zheming Liang, Yibin Wang, Jiaqi Wang

Abstract: Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its rendered-image counterpart should leave model performance essentially unaffected. In practice, however, such modality substitution induces dramatic performance… ▽ More Vision-Language Models (VLMs) have achieved substantial progress across a wide range of understanding and reasoning tasks, driven by large-scale image-text training aimed at multimodal fusion. Ideally, replacing a textual question with its rendered-image counterpart should leave model performance essentially unaffected. In practice, however, such modality substitution induces dramatic performance degradation. We attribute this "carrier sensitivity" issue to an inherent bias in current training corpora. Across prevalent datasets such as image captioning, VQA, OCR, and web-sourced interleaved data, text and images are typically organized into distinct and asymmetric roles, with text serving as linguistic queries and images as visual references. Such data bias leads VLMs to exhibit distinct preferences for information acquisition across different modalities. Consequently, VLMs fail to align representations of semantically equivalent content across textual and visual carriers, making model reasoning fragile under modality substitution. To address this, we propose Local Modality Substitution (LoMo), a lightweight, architecture-agnostic data curation paradigm designed to provide supervision for cross-modal representational invariance between semantically equivalent text and image carriers. LoMo achieves this by reformulating single-modality prompts into seamlessly interleaved multimodal sequences. It dynamically selects target text spans and recasts them as rendered images, thereby preserving the same semantics across "text, visual, text" carriers. Extensive experiments across 13 diverse multimodal benchmarks demonstrate that LoMo significantly improves overall multimodal reasoning and yields deeper cross-modal fusion. Specifically, it delivers consistent gains across foundational models, improving over standard SFT by 2.67 points on LLaVA-OneVision-1.5-8B and 2.82 points on Qwen3.5-9B. △ Less

Submitted 28 May, 2026; originally announced May 2026.

A Clinically Validated Foundation Model for Comprehensive Lung Pathology Interpretation

Authors: Zhengrui Guo, Zhengyu Zhang, Jiabo Ma, Yihui Wang, Fengtao Zhou, Yingxue Xu, Ling Liang, Chenglong Zhao, Qi Xie, Jinbang Li, Shujing Guo, Fangyi Han, Zhijian Cen, Ziyi Liu, Cheng Jin, Junlin Hou, Zhixuan Chen, Yu Cai, Lijuan Qu, Shifu Chen, Yueping Liu, Zhe Wang, Xiuming Zhang, Muyan Cai, Li Liang , et al. (1 additional authors not shown)

Abstract: Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objectives. Although pan-cancer foundation models offer versatility, they lack subspecialty-level depth and have not been evaluated across clinical workflows or prospectively validated in real-world settings. We introduce Pulmo… ▽ More Pathological assessment guides lung cancer diagnosis, treatment selection, and prognostic evaluation, yet current CPath approaches rely on task-specific models for isolated objectives. Although pan-cancer foundation models offer versatility, they lack subspecialty-level depth and have not been evaluated across clinical workflows or prospectively validated in real-world settings. We introduce PulmoFoundation, a multi-center, prospectively validated, randomized controlled trial (RCT)-evaluated foundation model for comprehensive lung pathology assessment across pre-operative, intra-operative, and post-operative care. Built upon Virchow2 via subspecialty-specific pretraining using ~40,000 diagnostic H&E-stained whole-slide images (WSIs), PulmoFoundation was systematically evaluated on ~26,000 WSIs across 32 clinically relevant tasks. In addition to accurately predicting molecular markers and patient survival, our model achieves clinical-grade performance in core diagnostic tasks across biopsy, frozen section, and surgical resection slides. In a registered prospective study of 1,357 patients across 11 diagnostic tasks, our model achieved an average AUC of 92.3%. Using pre-specified triage thresholds, PulmoFoundation could reduce additional second-review burden for 68.8% of biopsies and 83.0% of frozen sections, and defer 44.5% of IHC stain orders, with PPVs of 1.000, 0.991, and 0.966. Beyond prospective validation, we conducted a crossover RCT with eight pathologists, in which AI assistance improved diagnostic accuracy across 5,264 case-reader pairs (91.7% w/ AI vs. 83.2% w/o AI). AI assistance also reduced median diagnostic time by 18.3%, increased diagnostic confidence by 9.0%, and improved inter-rater agreement from moderate (kappa = 0.55) to substantial (kappa = 0.76). Together, these evaluations support PulmoFoundation as a clinically validated decision-support system for lung pathology. △ Less

Submitted 17 July, 2026; v1 submitted 25 May, 2026; originally announced May 2026.

ChronoMedicalWorld: A Medical World Model for Learning Patient Trajectories from Longitudinal Care Data

Authors: Jiangyuan Wang, Xuyong Chen, Junwei He, Xu Xu, Shasha Xie, Fuman Han

Abstract: Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-disease care, yet existing electronic health record (EHR) models are predominantly discriminative, and general-purpose large language models drift under repeated interventions. We propose the \textbf{ChronoMedicalWorld Model (CMWM)}, an action-conditio… ▽ More Long-horizon clinical simulation -- predicting how a patient's physiology evolves over years under specified interventions -- is central to chronic-disease care, yet existing electronic health record (EHR) models are predominantly discriminative, and general-purpose large language models drift under repeated interventions. We propose the \textbf{ChronoMedicalWorld Model (CMWM)}, an action-conditioned latent world-model framework for learning patient trajectories from longitudinal care data. CMWM couples a joint-embedding state encoder with a wide action encoder that admits both structured intervention indicators and free-text communication embeddings, and trains a recurrent latent transition module under a six-term objective: next-observation supervision, next-latent prediction, SIGReg latent regularisation, and three physiology-aware shape priors (slope, continuity, large-jump penalty). A closed-loop rollout-prefix protocol matches training to deployment, so the model is optimised against the same multi-step error it exhibits at inference. As a concrete case study, we instantiate CMWM for annual estimated glomerular filtration rate (eGFR) trajectory forecasting in chronic kidney disease (CKD). On a 2{,}232-patient nephrology cohort, the CKD instantiation achieves a dynamic-50\% history rollout test mean absolute error (MAE) of 7.384 and root-mean-square error (RMSE) of 10.256, against 7.964 and 11.069 for a tuned GPT-5.5 structured-prompting baseline ($-7.28\%$ MAE, $-7.35\%$ RMSE), with the gain dominated by the dialogue portion of patient--health-coach communication. The framework is not CKD-specific: its architecture, loss design, and training protocol apply to any chronic condition that can be cast as periodic clinical state interleaved with structured and conversational interventions. △ Less

Submitted 20 May, 2026; originally announced May 2026.

Comments: 14 pages, 2 figures, 6 tables

LLM Agents Enable User-Governed Personalization Beyond Platform Boundaries

Authors: Jiacheng Lin, Kun Qian, Arvind Srinivasan, Tian Wang, Fang Han, Changran Hu, Junze Liu, Ziyi Wang, Hanwen Xu, Mengmeng Xue, Shuo Yang, Hansi Zeng, Simon Sinong Zhan, Kai Zhong, Weiqi Zhang, Dakuo Wang, Tianhao Wang, Zhiyuan Li

Abstract: Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete picture of the user, as competitive incentives, legal constraints, user privacy concerns, and epistemic limits create persistent data barriers. This paper argues for a shift from platform-centric personalization to user-go… ▽ More Personalization today is fundamentally platform-centric: services build user representations from the behavioral fragments they observe. Yet no platform can construct a complete picture of the user, as competitive incentives, legal constraints, user privacy concerns, and epistemic limits create persistent data barriers. This paper argues for a shift from platform-centric personalization to user-governed personalization, where only the user can integrate fragmented contexts across platforms and the offline world. The key asymmetry lies in data access: only users can aggregate their own cross-platform and offline information. Large language model (LLM) agents make such integration practically feasible for the first time by enabling reasoning over heterogeneous personal data and transforming users' cross-context information into actionable personalization capabilities. We provide proof-of-concept evidence that users equipped with cross-platform data exports and an off-the-shelf LLM agent can outperform single-platform personalization baselines. We conclude by outlining a research agenda for building scalable user-governed personalization systems. △ Less

Submitted 10 May, 2026; originally announced May 2026.

Can Multimodal Large Language Models Truly Understand Small Objects?

Authors: Fujun Han, Junan Chen, Xintong Zhu, Jingqi Ye, Xuanjie Mao, Tao Chen, Peng Ye

Abstract: Multimodal Large Language Models (MLLMs) have shown promising potential in diverse understanding tasks, e.g., image and video analysis, math and physics olympiads. However, they remain blank and unexplored for Small Object Understanding (SOU) tasks. To fill this gap, we introduce SOUBench, the first and comprehensive benchmark for exploring the small objects understanding capability of existing ML… ▽ More Multimodal Large Language Models (MLLMs) have shown promising potential in diverse understanding tasks, e.g., image and video analysis, math and physics olympiads. However, they remain blank and unexplored for Small Object Understanding (SOU) tasks. To fill this gap, we introduce SOUBench, the first and comprehensive benchmark for exploring the small objects understanding capability of existing MLLMs. Specifically, we first design an effective and automatic visual question-answer generation strategy, constructing a new SOU-VQA evaluation dataset, with 18,204 VQA pairs, six relevant sub-tasks, and three dominant scenarios (i.e., Driving, Aerial, and Underwater). Then, we conduct a comprehensive evaluation on 15 state-of-the-art MLLMs and reveal their weak capabilities in small object understanding. Furthermore, we develop SOU-Train, a multimodal training dataset with 11,226 VQA pairs, to improve the SOU capabilities of MLLMs. Through supervising fine-tuning of the latest MLLM, we demonstrate that SOU-Train can effectively enhance the latest MLLM's ability to understand small objects. Comprehensive experimental results demonstrate that, the proposed SOUBench, along with the SOU-VQA and SOU-Train datasets, provides a crucial empirical foundation to the community for further developing models with enhanced small object understanding capabilities. Datasets and Code: https://github.com/Hanfj-X/SOU. △ Less

Submitted 24 April, 2026; originally announced April 2026.

Comments: Under Peer Review (26 pages, 9 figures, 6 tables)

From Debate to Decision: Conformal Social Choice for Safe Multi-Agent Deliberation

Authors: Mengdie Flora Wang, Haochen Xie, Guanghui Wang, Aijing Gao, Guang Yang, Ziyuan Li, Qucy Wei Qiu, Fangwei Han, Hengzhi Qiu, Yajing Huang, Bing Zhu, Jae Oh Woo

Abstract: Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action with no recourse. We introduce Conformal Social Choice, a post-hoc decision layer that converts debate outputs into calibrated act-versus-escalate decisions. Verb… ▽ More Multi-agent debate improves LLM reasoning, yet agreement among agents is not evidence of correctness. When agents converge on a wrong answer through social reinforcement, consensus-based stopping commits that error to an automated action with no recourse. We introduce Conformal Social Choice, a post-hoc decision layer that converts debate outputs into calibrated act-versus-escalate decisions. Verbalized probability distributions from heterogeneous agents are aggregated via a linear opinion pool and calibrated with split conformal prediction, yielding prediction sets with a marginal coverage guarantee: the correct answer is included with probability ${\geq}\,1{-}α$, without assumptions on individual model calibration. A hierarchical action policy maps singleton sets to autonomous action and larger sets to human escalation. On eight MMLU-Pro domains with three agents (Claude Haiku, DeepSeek-R1, Qwen-3 32B), coverage stays within 1--2 points of the target. The key finding is not that debate becomes more accurate, but that the conformal layer makes its failures actionable: 81.9% of wrong-consensus cases are intercepted at $α{=}0.05$. Because the layer refuses to act on cases where debate is confidently wrong, the remaining conformal singletons reach 90.0--96.8% accuracy (up to 22.1pp above consensus stopping) -- a selection effect, not a reasoning improvement. This safety comes at the cost of automation, but the operating point is user-adjustable via $α$. △ Less

Submitted 8 April, 2026; originally announced April 2026.

ThinknCheck: Grounded Claim Verification with Compact, Reasoning-Driven, and Interpretable Models

Authors: Delip Rao, Feijiang Han, Chris Callison-Burch

Abstract: We present ThinknCheck, a 1B-parameter verifier for grounded claim verification that first produces a short, structured rationale and then a binary verdict. We construct LLMAggreFact-Think, a 24.1k reasoning-augmented training set derived from LLMAggreFact, and fine-tune a 4-bit Gemma3 model to follow this format. On LLMAggreFact, ThinknCheck attains 78.1 balanced accuracy (BAcc), surpassing MiniC… ▽ More We present ThinknCheck, a 1B-parameter verifier for grounded claim verification that first produces a short, structured rationale and then a binary verdict. We construct LLMAggreFact-Think, a 24.1k reasoning-augmented training set derived from LLMAggreFact, and fine-tune a 4-bit Gemma3 model to follow this format. On LLMAggreFact, ThinknCheck attains 78.1 balanced accuracy (BAcc), surpassing MiniCheck-7B (77.4) with 7x fewer parameters; removing the reasoning step reduces BAcc to 57.5. On SciFact, ThinknCheck reaches 64.7 BAcc, a +14.7 absolute gain over MiniCheck-7B. By contrast, zero-shot chain-of-thought on the base Gemma3-1B harms accuracy relative to direct answers, and preference optimization with a simple format+accuracy reward underperforms supervised reasoning. To probe the latter, we introduce GSMClaims and a domain-specialized variant, ThinknCheck-Science, which improves across benchmarks, including 61.0\% accuracy on GSMClaims. Overall, explicit, supervised reasoning enables compact verifiers that are competitive while remaining resource-efficient and interpretable. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: 15 pages

The Missing Adapter Layer for Research Computing

Authors: Bowen Li, Jiazhu Xie, Chelsea Wang, Alessandro Umberto D'Aloia, Ziqi Xu, Fengling Han

Abstract: Higher Degree by Research (HDR) candidates increasingly depend on cloud-provisioned virtual machines and local GPU hardware for their computational experiments, yet a persistent and under-addressed gap separates having compute resources from using them productively. Cloud and infrastructure teams can provision a virtual machine in minutes, but the path from a raw VM to a reproducible, GPU-ready re… ▽ More Higher Degree by Research (HDR) candidates increasingly depend on cloud-provisioned virtual machines and local GPU hardware for their computational experiments, yet a persistent and under-addressed gap separates having compute resources from using them productively. Cloud and infrastructure teams can provision a virtual machine in minutes, but the path from a raw VM to a reproducible, GPU-ready research environment remains a significant barrier for researchers who are domain experts, not systems engineers. We argue that this gap is not a shortcoming of any particular tool but a missing architectural layer: an adapter layer that bridges cloud provisioning and interactive research work. We present a lightweight, open-source implementation of this layer, built on k3s and Coder and already in active use in our research workspace environment. A CI/CD pipeline connects GitHub directly to the local cluster, carrying a research project from commit to a running, accessible workspace in under five minutes. We then define a concrete metrics framework for evaluating any adapter layer covering deployment latency, environment reproducibility, onboarding friction, and resource utilisation and establish baselines against which improvements can be measured. △ Less

Submitted 20 July, 2026; v1 submitted 25 March, 2026; originally announced March 2026.

Comments: V3.0 version

Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty

Authors: Zhihao Pei, Nir Lipovetzky, Angela M. Rojas-Arevalo, Fjalar J. de Haan, Enayat A. Moallemi

Abstract: Socio-environmental planning under deep uncertainty requires researchers to identify and conceptualize problems before exploring policies and deploying plans. In practice and model-based planning approaches, this problem conceptualization process often relies on participatory modeling to translate stakeholders' natural-language descriptions into a quantitative model, making this process complex an… ▽ More Socio-environmental planning under deep uncertainty requires researchers to identify and conceptualize problems before exploring policies and deploying plans. In practice and model-based planning approaches, this problem conceptualization process often relies on participatory modeling to translate stakeholders' natural-language descriptions into a quantitative model, making this process complex and time-consuming. To facilitate this process, we propose a templated workflow that uses large language models for an initial conceptualization process. During the workflow, researchers can use large language models to identify the essential model components from stakeholders' intuitive problem descriptions, explore their diverse perspectives approaching the problem, assemble these components into a unified model, and eventually implement the model in Python through iterative communication. These results will facilitate the subsequent socio-environmental planning under deep uncertainty steps. Using ChatGPT 5.2 Instant, we demonstrated this workflow on the lake problem and an electricity market problem, both of which demonstrate socio-environmental planning problems. In both cases, acceptable outputs were obtained after a few iterations with human verification and refinement. These experiments indicated that large language models can serve as an effective tool for facilitating participatory modeling in the problem conceptualization process in socio-environmental planning. △ Less

Submitted 19 March, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Verified Multi-Agent Orchestration: A Plan-Execute-Verify-Replan Framework for Complex Query Resolution

Authors: Xing Zhang, Yanwei Cui, Guanghui Wang, Wei Qiu, Ziyuan Li, Fangwei Han, Yajing Huang, Hengzhi Qiu, Bing Zhu, Peiyang He

Abstract: We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to a… ▽ More We present Verified Multi-Agent Orchestration (VMAO), a framework that coordinates specialized LLM-based agents through a verification-driven iterative loop. Given a complex query, our system decomposes it into a directed acyclic graph (DAG) of sub-questions, executes them through domain-specific agents in parallel, verifies result completeness via LLM-based evaluation, and adaptively replans to address gaps. The key contributions are: (1) dependency-aware parallel execution over a DAG of sub-questions with automatic context propagation, (2) verification-driven adaptive replanning that uses an LLM-based verifier as an orchestration-level coordination signal, and (3) configurable stop conditions that balance answer quality against resource usage. On 25 expert-curated market research queries, VMAO improves answer completeness from 3.1 to 4.2 and source quality from 2.6 to 4.1 (1-5 scale) compared to a single-agent baseline, demonstrating that orchestration-level verification is an effective mechanism for multi-agent quality assurance. △ Less

Submitted 15 March, 2026; v1 submitted 11 March, 2026; originally announced March 2026.

Comments: ICLR 2026 Workshop on MALGAI

vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models

Authors: Xunzhuo Liu, Huamin Chen, Samzong Lu, Yossi Ovadia, Guohong Wen, Hao Wu, Zhengda Tan, Jintao Zhang, Senan Zedan, Yehudit Kerido, Liav Weiss, Haichen Zhang, Bishen Yu, Asaad Balum, Noa Limoy, Abdallah Samara, Baofa Fan, Brent Salisbury, Ryan Cook, Zhijie Wang, Qiping Pan, Rehan Khan, Avishek Goswami, Houston H. Zhang, Shuyi Wang , et al. (8 additional authors not shown)

Abstract: As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing: selecting the right model for each query at inference time, has become a critical systems challenge. We present vLLM Semantic Router, a signal-driven decision routing framework for Mixture-of-Modality (MoM) model deployments. The architecture follows two complem… ▽ More As large language models (LLMs) diversify across modalities, capabilities, and cost profiles, the problem of intelligent request routing: selecting the right model for each query at inference time, has become a critical systems challenge. We present vLLM Semantic Router, a signal-driven decision routing framework for Mixture-of-Modality (MoM) model deployments. The architecture follows two complementary Shannon-inspired views. In the information-theoretic regime, signal extraction reduces the entropy of "which model?" by distilling routing-relevant information from raw queries. In the Boolean-algebraic regime, the decision engine composes functionally complete routing policies from signal conditions. The central innovation is composable signal orchestration: thirteen heterogeneous signal types, spanning sub-millisecond heuristics and neural classifiers for semantics, safety, and modality, are composed through configurable Boolean decision rules into deployment-specific routing policies, so that fundamentally different scenarios (multi-cloud enterprise, privacy-regulated, cost-optimized) are expressed as different configurations over the same architecture. Matched decisions drive semantic model routing via thirteen selection algorithms, while per-decision plugin chains enforce safety constraints including a three-stage HaluGate hallucination detection pipeline and a lightweight episodic memory system with ReflectionGate for personalized multi-turn context. A typed neural-symbolic DSL specifies these routing policies and compiles them to multiple deployment targets, enabling configuration-first adaptation without code changes. Together, these components show that composable signal orchestration enables a single framework to serve diverse deployment scenarios with differentiated cost, privacy, and safety policies. △ Less

Submitted 3 June, 2026; v1 submitted 23 February, 2026; originally announced March 2026.

Comments: Technical Report

Swimming Under Constraints: A Safe Reinforcement Learning Framework for Quadrupedal Bio-Inspired Propulsion

Authors: Xinyu Cui, Fei Han, Hang Xu, Yongcheng Zeng, Luoyang Sun, Ruizhi Zhang, Jian Zhao, Haifeng Zhang, Weikun Li, Hao Chen, Jun Wang, Dixia Fan

Abstract: Bio-inspired aquatic propulsion offers high thrust and maneuverability but is prone to destabilizing forces such as lift fluctuations, which are further amplified by six-degree-of-freedom (6-DoF) fluid coupling. We formulate quadrupedal swimming as a constrained optimization problem that maximizes forward thrust while minimizing destabilizing fluctuations. Our proposed framework, Accelerated Const… ▽ More Bio-inspired aquatic propulsion offers high thrust and maneuverability but is prone to destabilizing forces such as lift fluctuations, which are further amplified by six-degree-of-freedom (6-DoF) fluid coupling. We formulate quadrupedal swimming as a constrained optimization problem that maximizes forward thrust while minimizing destabilizing fluctuations. Our proposed framework, Accelerated Constrained Proximal Policy Optimization with a PID-regulated Lagrange multiplier (ACPPO-PID), enforces constraints with a PID-regulated Lagrange multiplier, accelerates learning via conditional asymmetric clipping, and stabilizes updates through cycle-wise geometric aggregation. Initialized with imitation learning and refined through on-hardware towing-tank experiments, ACPPO-PID produces control policies that transfer effectively to quadrupedal free-swimming trials. Results demonstrate improved thrust efficiency, reduced destabilizing forces, and faster convergence compared with state-of-the-art baselines, underscoring the importance of constraint-aware safe RL for robust and generalizable bio-inspired locomotion in complex fluid environments. △ Less

Submitted 4 March, 2026; originally announced March 2026.

A Tree-Structured Two-Phase Commit Framework for OceanBase: Optimizing Scalability and Consistency

Authors: Quanqing Xu, Chen Qian, Chuanhui Yang, Fanyu Kong, Guixiang Liu, Fusheng Han, Zixiang Zhai

Abstract: Modern distributed databases face challenges in achieving transactional consistency across distributed partitions. Traditional two-phase commit (2PC) protocols incur high coordination overhead and latency, and require complex recovery for dynamic partition transfers. This paper introduces a novel tree-shaped 2PC framework for OceanBase that leverages single-machine log streams to address these cha… ▽ More Modern distributed databases face challenges in achieving transactional consistency across distributed partitions. Traditional two-phase commit (2PC) protocols incur high coordination overhead and latency, and require complex recovery for dynamic partition transfers. This paper introduces a novel tree-shaped 2PC framework for OceanBase that leverages single-machine log streams to address these challenges through three innovations. First, we propose log streams as atomic participants, replacing partition-level coordination. By treating each log stream as the commit unit, a transaction spanning $N$ co-located partitions interacts with one participant, reducing coordination overhead by orders of magnitude (e.g., 99 percent reduction for $N=100$). Second, we design a tree-shaped 2PC protocol with coordinator-rooted DAG topology that dynamically handles partition transfers by recursively constructing commit trees. When a partition migrates during a transaction, the protocol embeds migration contexts as leaf nodes, eliminating explicit participant list updates, resolving circular dependencies, and ensuring linearizable commits under topology changes. Third, we introduce prepare-unknown and trans-unknown states to prevent consistency violations when participants lose context. These states signal uncertainty during retries, avoiding erroneous aborts from so-called lying participants while isolating users from ambiguity. Experimental evaluation demonstrates performance approaching that of single-machine transactions, with reduced latency and bandwidth consumption, validating the framework's effectiveness for modern distributed databases. △ Less

Submitted 28 February, 2026; originally announced March 2026.

DeepAFL: Deep Analytic Federated Learning

Authors: Jianheng Tang, Yajiang Huang, Kejia Fan, Feijiang Han, Jiaxu Li, Jinfeng Xu, Run He, Anfeng Liu, Houbing Herbert Song, Huiping Zhuang, Yunhuai Liu

Abstract: Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on gradient-based updates, facing significant issues about heterogeneity, scalability, convergence, and overhead, etc. Recently, some analytic-learning-based work has attempted to handle these issues by eliminating gradient-based updates via analytical (i.e., closed-fo… ▽ More Federated Learning (FL) is a popular distributed learning paradigm to break down data silo. Traditional FL approaches largely rely on gradient-based updates, facing significant issues about heterogeneity, scalability, convergence, and overhead, etc. Recently, some analytic-learning-based work has attempted to handle these issues by eliminating gradient-based updates via analytical (i.e., closed-form) solutions. Despite achieving superior invariance to data heterogeneity, these approaches are fundamentally limited by their single-layer linear model with a frozen pre-trained backbone. As a result, they can only achieve suboptimal performance due to their lack of representation learning capabilities. In this paper, to enable representable analytic models while preserving the ideal invariance to data heterogeneity for FL, we propose our Deep Analytic Federated Learning approach, named DeepAFL. Drawing inspiration from the great success of ResNet in gradient-based learning, we design gradient-free residual blocks in our DeepAFL with analytical solutions. We introduce an efficient layer-wise protocol for training our deep analytic models layer by layer in FL through least squares. Both theoretical analyses and empirical evaluations validate our DeepAFL's superior performance with its dual advantages in heterogeneity invariance and representation learning, outperforming state-of-the-art baselines by up to 5.68%-8.42% across three benchmark datasets. △ Less

Submitted 28 February, 2026; originally announced March 2026.

Comments: Accepted in the Fourteenth International Conference on Learning Representations (ICLR 2026)

OceanBase Bacchus: a High-Performance and Scalable Cloud-Native Shared Storage Architecture for Multi-Cloud

Authors: Quanqing Xu, Mingqiang Zhuang, Chuanhui Yang, Quanwei Wan, Fusheng Han, Fanyu Kong, Hao Liu, Hu Xu, Junyu Ye

Abstract: Although an increasing number of databases now embrace shared-storage architectures, current storage-disaggregated systems have yet to strike an optimal balance between cost and performance. In high-concurrency read/write scenarios, B+-tree-based shared storage struggles to efficiently absorb frequent in-place updates. Existing LSM-tree-backed disaggregated storage designs are hindered by the intr… ▽ More Although an increasing number of databases now embrace shared-storage architectures, current storage-disaggregated systems have yet to strike an optimal balance between cost and performance. In high-concurrency read/write scenarios, B+-tree-based shared storage struggles to efficiently absorb frequent in-place updates. Existing LSM-tree-backed disaggregated storage designs are hindered by the intricate implementation of cross-node shared-log mechanisms, where no satisfactory solution yet exists. This paper presents OceanBase Bacchus, an LSM-tree architecture tailored for object storage provided by cloud vendors. The system sustains high-performance reads and writes while rendering compute nodes stateless through shared service-oriented PALF (Paxos-backed Append-only Log File system) logging and asynchronous background services. We employ a Shared Block Cache Service to flexibly utilize cache resources. Our design places log synchronization into a shared service, providing a novel solution for log sharing in storage-compute-separated databases. The architecture decouples functionality across modules, enabling elastic scaling where compute, cache, and storage resources can be resized rapidly and independently. Through experimental evaluation using multiple benchmark tests, including SysBench and TPC-H, we confirm that OceanBase Bacchus achieves performance comparable to or superior to that of HBase in OLTP scenarios and significantly outperforms StarRocks in OLAP workloads. Leveraging Bacchus's support for multi-cloud deployment and consistent performance, we not only retain high availability and competitive performance but also achieve substantial reductions in storage costs by 59% in OLTP scenarios and 89% in OLAP scenarios. △ Less

Submitted 26 February, 2026; originally announced February 2026.

The Quantization Trap: Breaking Linear Scaling Laws in Multi-Hop Reasoning

Authors: Henry Han, Xiyang Liu, Xiaodong Wang, Fei Han, Xiaodong Li

Abstract: Neural scaling laws provide a predictable recipe for AI advancement: reducing numerical precision should linearly improve computational efficiency and energy profile ($E \propto \mathrm{bits}$). In this paper, we demonstrate that this scaling law breaks in the context of multi-hop reasoning. We reveal a 'quantization trap' where reducing precision from 16-bit to 8/4-bit paradoxically increases net… ▽ More Neural scaling laws provide a predictable recipe for AI advancement: reducing numerical precision should linearly improve computational efficiency and energy profile ($E \propto \mathrm{bits}$). In this paper, we demonstrate that this scaling law breaks in the context of multi-hop reasoning. We reveal a 'quantization trap' where reducing precision from 16-bit to 8/4-bit paradoxically increases net energy consumption while degrading reasoning accuracy. We provide a rigorous theoretical decomposition that attributes this failure to hardware casting overhead, the hidden latency cost of dequantization kernels, which becomes a dominant bottleneck in sequential reasoning chains, as well as to a sequential energy amortization failure. As a result, scaling law breaking is unavoidable in practice. We formalize a Critical Model Scale $N^*$ that predicts when the trap dissolves or deepens as a function of model size, batch size, and hardware configuration, validated across a 120$\times$ range (0.6B--72B) on six GPU architectures. Our findings suggest that the industry's "smaller-is-better" heuristic is mathematically counterproductive for complex reasoning tasks. △ Less

Submitted 1 May, 2026; v1 submitted 13 February, 2026; originally announced February 2026.

Comments: 23 pages, 8 figures

DeepGen 1.0: A Lightweight Unified Multimodal Model for Advancing Image Generation and Editing

Authors: Dianyi Wang, Ruihang Li, Feng Han, Chaofan Ma, Wei Song, Siyuan Wang, Yibin Wang, Yi Xin, Hongjian Liu, Zhixiong Zhang, Shengyuan Ding, Tianhang Wang, Zhenglin Cheng, Tao Lin, Cheng Jin, Kaicheng Yu, Jingjing Chen, Wenjie Wang, Zhongyu Wei, Jiaqi Wang

Abstract: Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight 5B unified model that achieves comprehensive capabilities competitive with or surpassing much larger counterparts. To overcome the limitations of compact models… ▽ More Current unified multimodal models for image generation and editing typically rely on massive parameter scales (e.g., >10B), entailing prohibitive training costs and deployment footprints. In this work, we present DeepGen 1.0, a lightweight 5B unified model that achieves comprehensive capabilities competitive with or surpassing much larger counterparts. To overcome the limitations of compact models in semantic understanding and fine-grained control, we introduce Stacked Channel Bridging (SCB), a deep alignment framework that extracts hierarchical features from multiple VLM layers and fuses them with learnable 'think tokens' to provide the generative backbone with structured, reasoning-rich guidance. We further design a data-centric training strategy spanning three progressive stages: (1) Alignment Pre-training on large-scale image-text pairs and editing triplets to synchronize VLM and DiT representations, (2) Joint Supervised Fine-tuning on a high-quality mixture of generation, editing, and reasoning tasks to foster omni-capabilities, and (3) Reinforcement Learning with MR-GRPO, which leverages a mixture of reward functions and supervision signals, resulting in substantial gains in generation quality and alignment with human preferences, while maintaining stable training progress and avoiding visual artifacts. Despite being trained on only ~50M samples, DeepGen 1.0 achieves leading performance across diverse benchmarks, surpassing the 80B HunyuanImage by 28% on WISE and the 27B Qwen-Image-Edit by 37% on UniREditBench. By open-sourcing our training code, weights, and datasets, we provide an efficient, high-performance alternative to democratize unified multimodal research. △ Less

Submitted 13 February, 2026; v1 submitted 12 February, 2026; originally announced February 2026.

Building an OceanBase-based Distributed Nearly Real-time Analytical Processing Database System

Authors: Quanqing Xu, Chuanhui Yang, Ruijie Li, Dongdong Xie, Hui Cao, Yi Xiao, Junquan Chen, Yanzuo Wang, Saitong Zhao, Fusheng Han, Bin Liu, Guoping Wang, Yuzhong Zhao, Mingqiang Zhuang

Abstract: The growing demand for database systems capable of efficiently managing massive datasets while delivering real-time transaction processing and advanced analytical capabilities has become critical in modern data infrastructure. While traditional OLAP systems often fail to meet these dual requirements, emerging real-time analytical processing systems still face persistent challenges, such as excessi… ▽ More The growing demand for database systems capable of efficiently managing massive datasets while delivering real-time transaction processing and advanced analytical capabilities has become critical in modern data infrastructure. While traditional OLAP systems often fail to meet these dual requirements, emerging real-time analytical processing systems still face persistent challenges, such as excessive data redundancy, complex cross-system synchronization, and suboptimal temporal efficiency. This paper introduces OceanBase Mercury as an innovative OLAP system designed for petabyte-scale data. The system features a distributed, multi-tenant architecture that ensures essential enterprise-grade requirements, including continuous availability and elastic scalability. Our technical contributions include three key components: (1) an adaptive columnar storage format with hybrid data layout optimization, (2) a differential refresh mechanism for materialized views with temporal consistency guarantees, and (3) a polymorphic vectorization engine supporting three distinct data formats. Empirical evaluations under real-world workloads demonstrate that OceanBase Mercury outperforms specialized OLAP engines by 1.3X to 3.1X speedup in query latency while maintaining sub-second latency, positioning it as a groundbreaking AP solution that effectively balances analytical depth with operational agility in big data environments. △ Less

Submitted 7 February, 2026; originally announced February 2026.

UniReason 1.0: A Unified Reasoning Framework for World Knowledge Aligned Image Generation and Editing

Authors: Dianyi Wang, Chaofan Ma, Feng Han, Size Wu, Wei Song, Yibin Wang, Zhixiong Zhang, Tianhang Wang, Siyuan Wang, Zhongyu Wei, Jiaqi Wang

Abstract: Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through two complementary reasoning paradigms. We incorporate world knowledge-e… ▽ More Unified multimodal models often struggle with complex synthesis tasks that demand deep reasoning, and typically treat text-to-image generation and image editing as isolated capabilities rather than interconnected reasoning steps. To address this, we propose UniReason, a unified framework that harmonizes these two tasks through two complementary reasoning paradigms. We incorporate world knowledge-enhanced textual reasoning into generation to infer implicit knowledge, and leverage editing capabilities for fine-grained editing-like visual refinement to further correct visual errors via self-reflection. This approach unifies generation and editing within a shared architecture, mirroring the human cognitive process of planning followed by refinement. We support this framework by systematically constructing a large-scale reasoning-centric dataset (~300k samples) covering five major knowledge domains (e.g., cultural commonsense, physics, etc.) for textual reasoning, alongside an agent-generated corpus for visual refinement. Extensive experiments demonstrate that UniReason achieves advanced performance on reasoning-intensive benchmarks such as WISE, KrisBench and UniREditBench, while maintaining superior general synthesis capabilities. △ Less

Submitted 20 February, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Unified Personalized Reward Model for Vision Generation

Authors: Yibin Wang, Yuhang Zang, Feng Han, Jiazi Bu, Yujie Zhou, Cheng Jin, Jiaqi Wang

Abstract: Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and subsequently optimize visual generation models via reinforcement learning. However, current RMs suffer from inherent limitations: they often follow a one-size-f… ▽ More Recent advancements in multimodal reward models (RMs) have significantly propelled the development of visual generation. Existing frameworks typically adopt Bradley-Terry-style preference modeling or leverage generative VLMs as judges, and subsequently optimize visual generation models via reinforcement learning. However, current RMs suffer from inherent limitations: they often follow a one-size-fits-all paradigm that assumes a monolithic preference distribution or relies on fixed evaluation rubrics. As a result, they are insensitive to content-specific visual cues, leading to systematic misalignment with subjective and context-dependent human preferences. To this end, inspired by human assessment, we propose UnifiedReward-Flex, a unified personalized reward model for vision generation that couples reward modeling with flexible and context-adaptive reasoning. Specifically, given a prompt and the generated visual content, it first interprets the semantic intent and grounds on visual evidence, then dynamically constructs a hierarchical assessment by instantiating fine-grained criteria under both predefined and self-generated high-level dimensions. Our training pipeline follows a two-stage process: (1) we first distill structured, high-quality reasoning traces from advanced closed-source VLMs to bootstrap SFT, equipping the model with flexible and context-adaptive reasoning behaviors; (2) we then perform direct preference optimization (DPO) on carefully curated preference pairs to further strengthen reasoning fidelity and discriminative alignment. To validate the effectiveness, we integrate UnifiedReward-Flex into the GRPO framework for image and video synthesis, and extensive results demonstrate its superiority. △ Less

Submitted 10 February, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Comments: Website: https://codegoat24.github.io/UnifiedReward/flex

Causal World Modeling for Robot Control

Authors: Lin Li, Qihang Zhang, Yiming Luo, Shuai Yang, Ruilin Wang, Fei Han, Mingrui Yu, Zelin Gao, Nan Xue, Xing Zhu, Yujun Shen, Yinghao Xu

Abstract: This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics. Inspired by this, we introduce LingBot-VA, an autoregressive diffusion framework that learns frame… ▽ More This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics. Inspired by this, we introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously. Our model features three carefully crafted designs: (1) a shared latent space, integrating vision and action tokens, driven by a Mixture-of-Transformers (MoT) architecture, (2) a closed-loop rollout mechanism, allowing for ongoing acquisition of environmental feedback with ground-truth observations, (3) an asynchronous inference pipeline, parallelizing action prediction and motor execution to support efficient control. We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations. The code and model are made publicly available to facilitate the community. △ Less

Submitted 22 March, 2026; v1 submitted 29 January, 2026; originally announced January 2026.

Comments: Project page: https://technology.robbyant.com/lingbot-va Code: https://github.com/robbyant/lingbot-va

VideoThinker: Building Agentic VideoLLMs with LLM-Guided Tool Reasoning

Authors: Chenglin Li, Qianglong Chen, Feng Han, Yikun Wang, Xingxi Yin, Yan Gong, Ruilin Li, Yin Zhang, Jiaqi Wang

Abstract: Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and leads to substantial information loss in long videos. Agentic tools such as temporal retrieval, spatial zoom, and temporal zoom offer a natural way to overcome these limitations by… ▽ More Long-form video understanding remains a fundamental challenge for current Video Large Language Models. Most existing models rely on static reasoning over uniformly sampled frames, which weakens temporal localization and leads to substantial information loss in long videos. Agentic tools such as temporal retrieval, spatial zoom, and temporal zoom offer a natural way to overcome these limitations by enabling adaptive exploration of key moments. However, constructing agentic video understanding data requires models that already possess strong long-form video comprehension, creating a circular dependency. We address this challenge with VideoThinker, an agentic Video Large Language Model trained entirely on synthetic tool interaction trajectories. Our key idea is to convert videos into rich captions and employ a powerful agentic language model to generate multi-step tool use sequences in caption space. These trajectories are subsequently grounded back to video by replacing captions with the corresponding frames, yielding a large-scale interleaved video and tool reasoning dataset without requiring any long-form understanding from the underlying model. Training on this synthetic agentic dataset equips VideoThinker with dynamic reasoning capabilities, adaptive temporal exploration, and multi-step tool use. Remarkably, VideoThinker significantly outperforms both caption-only language model agents and strong video model baselines across long-video benchmarks, demonstrating the effectiveness of tool augmented synthetic data and adaptive retrieval and zoom reasoning for long-form video understanding. △ Less

Submitted 19 April, 2026; v1 submitted 22 January, 2026; originally announced January 2026.

Securing LLM-as-a-Service for Small Businesses: An Industry Case Study of a Distributed Chatbot Deployment Platform

Authors: Jiazhu Xie, Bowen Li, Heyu Fu, Chong Gao, Ziqi Xu, Fengling Han

Abstract: Large Language Model (LLM)-based question-answering systems offer significant potential for automating customer support and internal knowledge access in small businesses, yet their practical deployment remains challenging due to infrastructure costs, engineering complexity, and security risks, particularly in retrieval-augmented generation (RAG)-based settings. This paper presents an industry case… ▽ More Large Language Model (LLM)-based question-answering systems offer significant potential for automating customer support and internal knowledge access in small businesses, yet their practical deployment remains challenging due to infrastructure costs, engineering complexity, and security risks, particularly in retrieval-augmented generation (RAG)-based settings. This paper presents an industry case study of an open-source, multi-tenant platform that enables small businesses to deploy customised LLM-based support chatbots via a no-code workflow. The platform is built on distributed, lightweight k3s clusters spanning heterogeneous, low-cost machines and interconnected through an encrypted overlay network, enabling cost-efficient resource pooling while enforcing container-based isolation and per-tenant data access controls. In addition, the platform integrates practical, platform-level defences against prompt injection attacks in RAG-based chatbots, translating insights from recent prompt injection research into deployable security mechanisms without requiring model retraining or enterprise-scale infrastructure. We evaluate the proposed platform through a real-world e-commerce deployment, demonstrating that secure and efficient LLM-based chatbot services can be achieved under realistic cost, operational, and security constraints faced by small businesses. △ Less

Submitted 21 January, 2026; originally announced January 2026.

Comments: Accepted by AISC 2026

Journal ref: Australasian Information Security Conference 2026

Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models

Authors: Hengyuan Zhang, Zhihao Zhang, Mingyang Wang, Zunhai Su, Yiwei Wang, Qianli Wang, Shuzhou Yuan, Ercong Nie, Xufeng Duan, Feijiang Han, Qibo Xue, Zeping Yu, Chenming Shang, Xiao Liang, Jing Xiong, Hui Shen, Chaofan Tao, Zhengwu Liu, Senjie Jin, Zhiheng Xi, Dongdong Zhang, Sophia Ananiadou, Tao Gui, Ruobing Xie, Hayden Kwok-Hay So , et al. (4 additional authors not shown)

Abstract: Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate… ▽ More Mechanistic Interpretability (MI) has emerged as a vital approach to demystify the opaque decision-making of Large Language Models (LLMs). However, existing reviews primarily treat MI as an observational science, summarizing analytical insights while lacking a systematic framework for actionable intervention. To bridge this gap, we present a practical survey structured around the pipeline: "Locate, Steer, and Improve." We formally categorize Localizing (diagnosis) and Steering (intervention) methods based on specific Interpretable Objects to establish a rigorous intervention protocol. Furthermore, we demonstrate how this framework enables tangible improvements in Alignment, Capability, and Efficiency, effectively operationalizing MI as an actionable methodology for model optimization. The curated paper list of this work is available at https://github.com/rattlesnakey/Awesome-Actionable-MI-Survey. △ Less

Submitted 13 April, 2026; v1 submitted 20 January, 2026; originally announced January 2026.

Kling-Omni Technical Report

Authors: Kling Team, Jialu Chen, Yuanzheng Ci, Xiangyu Du, Zipeng Feng, Kun Gai, Sainan Guo, Feng Han, Jingbin He, Kang He, Xiao Hu, Xiaohua Hu, Boyuan Jiang, Fangyuan Kong, Hang Li, Jie Li, Qingyu Li, Shen Li, Xiaohan Li, Yan Li, Jiajun Liang, Borui Liao, Yiqiao Liao, Weihong Lin, Quande Liu , et al. (43 additional authors not shown)

Abstract: We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supp… ▽ More We present Kling-Omni, a generalist generative framework designed to synthesize high-fidelity videos directly from multimodal visual language inputs. Adopting an end-to-end perspective, Kling-Omni bridges the functional separation among diverse video generation, editing, and intelligent reasoning tasks, integrating them into a holistic system. Unlike disjointed pipeline approaches, Kling-Omni supports a diverse range of user inputs, including text instructions, reference images, and video contexts, processing them into a unified multimodal representation to deliver cinematic-quality and highly-intelligent video content creation. To support these capabilities, we constructed a comprehensive data system that serves as the foundation for multimodal video creation. The framework is further empowered by efficient large-scale pre-training strategies and infrastructure optimizations for inference. Comprehensive evaluations reveal that Kling-Omni demonstrates exceptional capabilities in in-context generation, reasoning-based editing, and multimodal instruction following. Moving beyond a content creation tool, we believe Kling-Omni is a pivotal advancement toward multimodal world simulators capable of perceiving, reasoning, generating and interacting with the dynamic and complex worlds. △ Less

Submitted 18 December, 2025; originally announced December 2025.

Comments: Kling-Omni Technical Report

Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification

Authors: Feijiang Han

Abstract: Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant progress in WebShell detection (i.e., distinguishing malicious samples from benign ones), we argue that it is time to transition from passive detection to in-depth ana… ▽ More Malicious WebShells pose a significant and evolving threat by compromising critical digital infrastructures and endangering public services in sectors such as healthcare and finance. While the research community has made significant progress in WebShell detection (i.e., distinguishing malicious samples from benign ones), we argue that it is time to transition from passive detection to in-depth analysis and proactive defense. One promising direction is the automation of WebShell family classification, which involves identifying the specific malware lineage in order to understand an adversary's tactics and enable a precise, rapid response. This crucial task, however, remains a largely unexplored area that currently relies on slow, manual expert analysis. To address this gap, we present the first systematic study to automate WebShell family classification. Our method begins with extracting dynamic function call traces to capture inherent behaviors that are resistant to common encryption and obfuscation. To enhance the scale and diversity of our dataset for a more stable evaluation, we augment these real-world traces with new variants synthesized by Large Language Models. These augmented traces are then abstracted into sequences, graphs, and trees, providing a foundation to benchmark a comprehensive suite of representation methods. Our evaluation spans classic sequence-based embeddings (CBOW, GloVe), transformers (BERT, SimCSE), and a range of structure-aware algorithms, including Graph Kernels, Graph Edit Distance, Graph2Vec, and various Graph Neural Networks. Through extensive experiments on four real-world, family-annotated datasets under both supervised and unsupervised settings, we establish a robust baseline and provide practical insights into the most effective combinations of data abstractions, representation models, and learning paradigms for this challenge. △ Less

Submitted 4 December, 2025; originally announced December 2025.

Dual-LoRA and Quality-Enhanced Pseudo Replay for Multimodal Continual Food Learning

Authors: Xinlan Wu, Bin Zhu, Feng Han, Pengkun Jiao, Jingjing Chen

Abstract: Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, i… ▽ More Food analysis has become increasingly critical for health-related tasks such as personalized nutrition and chronic disease prevention. However, existing large multimodal models (LMMs) in food analysis suffer from catastrophic forgetting when learning new tasks, requiring costly retraining from scratch. To address this, we propose a novel continual learning framework for multimodal food learning, integrating a Dual-LoRA architecture with Quality-Enhanced Pseudo Replay. We introduce two complementary low-rank adapters for each task: a specialized LoRA that learns task-specific knowledge with orthogonal constraints to previous tasks' subspaces, and a cooperative LoRA that consolidates shared knowledge across tasks via pseudo replay. To improve the reliability of replay data, our Quality-Enhanced Pseudo Replay strategy leverages self-consistency and semantic similarity to reduce hallucinations in generated samples. Experiments on the comprehensive Uni-Food dataset show superior performance in mitigating forgetting, representing the first effective continual learning approach for complex food tasks. △ Less

Submitted 17 November, 2025; originally announced November 2025.

GrOCE:Graph-Guided Online Concept Erasure for Text-to-Image Diffusion Models

Authors: Ning Han, Zhenyu Ge, Feng Han, Yuhua Sun, Chengqing Li, Jingjing Chen

Abstract: Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods either rely on costly fine-tuning or apply coarse semantic separation, often degrading unrelated concepts and lacking adaptability to evolving concept sets. In this paper, we propose Graph-Guided Online Concept Erasure (G… ▽ More Concept erasure aims to remove harmful, inappropriate, or copyrighted content from text-to-image diffusion models while preserving non-target semantics. However, existing methods either rely on costly fine-tuning or apply coarse semantic separation, often degrading unrelated concepts and lacking adaptability to evolving concept sets. In this paper, we propose Graph-Guided Online Concept Erasure (GrOCE), a training-free framework that performs precise and context-aware online removal of target concepts. GrOCE constructs dynamic semantic graphs to identify clusters of target concepts and selectively suppress their influence within text prompts. It consists of three synergistic components: (1) dynamic semantic graph construction (Construct) incrementally builds a weighted graph over vocabulary concepts to capture semantic affinities; (2) adaptive cluster identification (Identify) extracts a target concept cluster through multi-hop traversal and diffusion-based scoring to quantify semantic influence; and (3) selective severing (Sever) removes semantic components associated with the target cluster from the text prompt while retaining non-target semantics and the global sentence structure. Extensive experiments demonstrate that GrOCE achieves state-of-the-art performance on the Concept Similarity (CS) and Fréchet Inception Distance (FID) metrics, offering efficient, accurate, and stable concept erasure. △ Less

Submitted 13 April, 2026; v1 submitted 16 November, 2025; originally announced November 2025.

Comments: Accepted to CVPR 2026 Highlight

MSC Class: Computer Vision and Pattern Recognition (cs.CV)

UniREditBench: A Unified Reasoning-based Image Editing Benchmark

Authors: Feng Han, Yibin Wang, Chenglin Li, Zheming Liang, Dianyi Wang, Yang Jiao, Zhipeng Wei, Chao Gong, Cheng Jin, Jiaqi Wang

Abstract: Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primaril… ▽ More Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-world scenarios that involve human-defined rules, which are common in real-life applications; (2) they only rely on textual references to evaluate the generated images, potentially leading to systematic misjudgments, especially in complex reasoning scenarios. To this end, this work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation. It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions. To improve evaluation reliability, we introduce multimodal dual-reference evaluation, providing both textual and ground-truth image references for each sample assessment. Furthermore, we design an automated multi-scenario data synthesis pipeline and construct UniREdit-Data-100K, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings. Through thorough benchmarking of both open-source and closed-source image editing models, we reveal their strengths and weaknesses across various aspects. △ Less

Submitted 7 August, 2026; v1 submitted 3 November, 2025; originally announced November 2025.

Comments: Project page: https://maplebb.github.io/UniREditBench

Sparse Transformer Architectures via Regularized Wasserstein Proximal Operator with $L_1$ Prior

Authors: Fuqun Han, Stanley Osher, Wuchen Li

Abstract: In this work, we propose a sparse transformer architecture that incorporates prior information about the underlying data distribution directly into the transformer structure of the neural network. The design of the model is motivated by a special optimal transport problem, namely the regularized Wasserstein proximal operator, which admits a closed-form solution and turns out to be a special repres… ▽ More In this work, we propose a sparse transformer architecture that incorporates prior information about the underlying data distribution directly into the transformer structure of the neural network. The design of the model is motivated by a special optimal transport problem, namely the regularized Wasserstein proximal operator, which admits a closed-form solution and turns out to be a special representation of transformer architectures. Compared with classical flow-based models, the proposed approach improves the convexity properties of the optimization problem and promotes sparsity in the generated samples. Through both theoretical analysis and numerical experiments, including applications in generative modeling and Bayesian inverse problems, we demonstrate that the sparse transformer achieves higher accuracy and faster convergence to the target distribution than classical neural ODE-based methods. △ Less

Submitted 18 October, 2025; originally announced October 2025.

Higher Satisfaction, Lower Cost: A Technical Report on How LLMs Revolutionize Meituan's Intelligent Interaction Systems

Authors: Xuxin Cheng, Ke Zeng, Zhiquan Cao, Linyi Dai, Wenxuan Gao, Fei Han, Ai Jian, Feng Hong, Wenxing Hu, Zihe Huang, Dejian Kong, Jia Leng, Zhuoyuan Liao, Pei Liu, Jiaye Lin, Xing Ma, Jingqing Ruan, Jiaxing Song, Xiaoyu Tan, Ruixuan Xiao, Wenhui Yu, Wenyu Zhan, Haoxing Zhang, Chao Zhou, Hao Zhou , et al. (43 additional authors not shown)

Abstract: Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction systems to deliver efficient, personalized, and 24/7 support. In practice, intelligent interaction systems encounter several challenges: (1) Constructing high-quality… ▽ More Enhancing customer experience is essential for business success, particularly as service demands grow in scale and complexity. Generative artificial intelligence and Large Language Models (LLMs) have empowered intelligent interaction systems to deliver efficient, personalized, and 24/7 support. In practice, intelligent interaction systems encounter several challenges: (1) Constructing high-quality data for cold-start training is difficult, hindering self-evolution and raising labor costs. (2) Multi-turn dialogue performance remains suboptimal due to inadequate intent understanding, rule compliance, and solution extraction. (3) Frequent evolution of business rules affects system operability and transferability, constraining low-cost expansion and adaptability. (4) Reliance on a single LLM is insufficient in complex scenarios, where the absence of multi-agent frameworks and effective collaboration undermines process completeness and service quality. (5) The open-domain nature of multi-turn dialogues, lacking unified golden answers, hampers quantitative evaluation and continuous optimization. To address these challenges, we introduce WOWService, an intelligent interaction system tailored for industrial applications. With the integration of LLMs and multi-agent architectures, WOWService enables autonomous task management and collaborative problem-solving. Specifically, WOWService focuses on core modules including data construction, general capability enhancement, business scenario adaptation, multi-agent coordination, and automated evaluation. Currently, WOWService is deployed on the Meituan App, achieving significant gains in key metrics, e.g., User Satisfaction Metric 1 (USM 1) -27.53% and User Satisfaction Metric 2 (USM 2) +25.51%, demonstrating its effectiveness in capturing user needs and advancing personalized service. △ Less

Submitted 14 January, 2026; v1 submitted 15 October, 2025; originally announced October 2025.

Comments: 36 pages, 14 figures

DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment

Authors: Zongcai Du, Guilin Deng, Xiaofeng Guo, Xin Gao, Linke Li, Kaichang Cheng, Fubo Han, Siyu Yang, Peng Liu, Pan Zhong, Qiang Fu

Abstract: Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-stage pipeline: a compact seed set of human-sung recordings is constructed by pairing fixed melodies with diverse LLM-generated lyrics, and melody-specific models are trained to synthesize over 500 hours of high-quality C… ▽ More Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-stage pipeline: a compact seed set of human-sung recordings is constructed by pairing fixed melodies with diverse LLM-generated lyrics, and melody-specific models are trained to synthesize over 500 hours of high-quality Chinese singing data. Building on this corpus, we propose DiTSinger, a Diffusion Transformer with RoPE and qk-norm, systematically scaled in depth, width, and resolution for enhanced fidelity. Furthermore, we design an implicit alignment mechanism that obviates phoneme-level duration labels by constraining phoneme-to-acoustic attention within character-level spans, thereby improving robustness under noisy or uncertain alignments. Extensive experiments validate that our approach enables scalable, alignment-free, and high-fidelity SVS. △ Less

Submitted 24 December, 2025; v1 submitted 10 October, 2025; originally announced October 2025.

Comments: ICASSP26 under review. Demo page: https://nju-jet.github.io/DiTSinger

EmbeddingGemma: Powerful and Lightweight Text Representations

Authors: Henrique Schechter Vera, Sahil Dua, Biao Zhang, Daniel Salz, Ryan Mullins, Sindhu Raghuram Panyam, Sara Smoot, Iftekhar Naim, Joe Zou, Feiyang Chen, Daniel Cer, Alice Lisak, Min Choi, Lucas Gonzalez, Omar Sanseviero, Glenn Cameron, Ian Ballantyne, Kat Black, Kaifeng Chen, Weiyi Wang, Zhe Li, Gus Martins, Jinhyuk Lee, Mark Sherwood, Juyeong Ji , et al. (64 additional authors not shown)

Abstract: We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoin… ▽ More We introduce EmbeddingGemma, a new lightweight, open text embedding model based on the Gemma 3 language model family. Our innovative training recipe strategically captures knowledge from larger models via encoder-decoder initialization and geometric embedding distillation. We improve model robustness and expressiveness with a spread-out regularizer, and ensure generalizability by merging checkpoints from varied, optimized mixtures. Evaluated on the Massive Text Embedding Benchmark (MTEB) across multilingual, English, and code domains, EmbeddingGemma (300M) achieves state-of-the-art results. Notably, it outperforms prior top models, both proprietary and open, with fewer than 500M parameters, and provides performance comparable to models double its size, offering an exceptional performance-to-cost ratio. Remarkably, this lead persists when quantizing model weights or truncating embedding outputs. This makes EmbeddingGemma particularly well-suited for low-latency and high-throughput use cases such as on-device applications. We provide ablation studies exploring our key design choices. We release EmbeddingGemma to the community to promote further research. △ Less

Submitted 1 November, 2025; v1 submitted 24 September, 2025; originally announced September 2025.

Comments: 18 pages. Models are available in HuggingFace (at https://huggingface.co/collections/google/embeddinggemma-68b9ae3a72a82f0562a80dc4), Kaggle (at https://www.kaggle.com/models/google/embeddinggemma/), and Vertex AI (at https://pantheon.corp.google.com/vertex-ai/publishers/google/model-garden/embeddinggemma)

VideoPro: Adaptive Program Reasoning for Long Video Understanding

Authors: Chenglin Li, Feng Han, Yikun Wang, Ruilin Li, Shuai Dong, Haowen Hou, Haitao Li, Qianglong Chen, Feng Tao, Jingqi Tong, Yin Zhang, Jiaqi Wang

Abstract: Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question answering (videoQA). To address these challenges, we introduce the FS-VisPR framework, an adaptive visual program reasoning approach that balances fast reasoning for s… ▽ More Large language models (LLMs) have shown promise in generating program workflows for visual tasks. However, previous approaches often rely on closed-source models, lack systematic reasoning, and struggle with long-form video question answering (videoQA). To address these challenges, we introduce the FS-VisPR framework, an adaptive visual program reasoning approach that balances fast reasoning for simple queries with slow reasoning for difficult ones. First, we design efficient visual modules (e.g., key clip retrieval and subtitle retrieval) to support long-form video tasks. Then, we construct a diverse and high-quality fast-slow reasoning dataset with a strong LLM to align open-source language models' ability to generate visual program workflows as FS-LLM. Next, we design a fast-slow reasoning framework with FS-LLM: Simple queries are directly solved by VideoLLMs, while difficult ones invoke visual program reasoning, motivated by human-like reasoning processes. During this process, low-confidence fast-thinking answers will trigger a second-stage slow-reasoning process, and a fallback mechanism to fast reasoning is activated if the program execution fails. Moreover, we improve visual programs through parameter search during both training and inference. By adjusting the parameters of the visual modules within the program, multiple variants are generated: during training, programs that yield correct answers are selected, while during inference, the program with the highest confidence result is applied. Experiments show that FS-VisPR improves both efficiency and reliability in visual program workflows. It achieves 50.4% accuracy on LVBench, surpassing GPT-4o, matching the performance of Qwen2.5VL-72B on VideoMME. △ Less

Submitted 25 January, 2026; v1 submitted 22 September, 2025; originally announced September 2025.

VCE: Safe Autoregressive Image Generation via Visual Contrast Exploitation

Authors: Feng Han, Chao Gong, Zhipeng Wei, Jingjing Chen, Yu-Gang Jiang

Abstract: Recently, autoregressive image generation models have wowed audiences with their remarkable capability in creating surprisingly realistic images. Models such as GPT-4o and LlamaGen can not only produce images that faithfully mimic renowned artistic styles like Ghibli, Van Gogh, or Picasso, but also potentially generate Not-Safe-For-Work (NSFW) content, raising significant concerns regarding copyri… ▽ More Recently, autoregressive image generation models have wowed audiences with their remarkable capability in creating surprisingly realistic images. Models such as GPT-4o and LlamaGen can not only produce images that faithfully mimic renowned artistic styles like Ghibli, Van Gogh, or Picasso, but also potentially generate Not-Safe-For-Work (NSFW) content, raising significant concerns regarding copyright infringement and ethical use. Despite these concerns, methods to safeguard autoregressive text-to-image models remain underexplored. Previous concept erasure methods, primarily designed for diffusion models that operate in denoising latent space, are not directly applicable to autoregressive models that generate images token by token. To address this critical gap, we propose Visual Contrast Exploitation (VCE), a novel framework comprising: (1) an innovative contrastive image pair construction paradigm that precisely decouples unsafe concepts from their associated content semantics, and (2) a sophisticated DPO-based training approach that enhances the model's ability to identify and leverage visual contrastive features from image pairs, enabling precise concept erasure. Our comprehensive experiments across three challenging tasks-artist style erasure, explicit content erasure, and object removal-demonstrate that our method effectively secures the model, achieving state-of-the-art results while erasing unsafe concepts and maintaining the integrity of unrelated safe concepts. The code and models are available at https://github.com/Maplebb/VCE. △ Less

Submitted 22 November, 2025; v1 submitted 21 September, 2025; originally announced September 2025.

Omni-LIVO: Robust RGB-Colored Multi-Camera Visual-Inertial-LiDAR Odometry via Photometric Migration and ESIKF Fusion

Authors: Yinong Cao, Chenyang Zhang, Xin He, Yuwei Chen, Chengyu Pu, Bingtao Wang, Kaile Wu, Shouzheng Zhu, Fei Han, Shijie Liu, Chunlai Li, Jianyu Wang

Abstract: Wide field-of-view (FoV) LiDAR sensors provide dense geometry across large environments, but existing LiDAR-inertial-visual odometry (LIVO) systems generally rely on a single camera, limiting their ability to fully exploit LiDAR-derived depth for photometric alignment and scene colorization. We present Omni-LIVO, a tightly coupled multi-camera LIVO system that leverages multi-view observations to… ▽ More Wide field-of-view (FoV) LiDAR sensors provide dense geometry across large environments, but existing LiDAR-inertial-visual odometry (LIVO) systems generally rely on a single camera, limiting their ability to fully exploit LiDAR-derived depth for photometric alignment and scene colorization. We present Omni-LIVO, a tightly coupled multi-camera LIVO system that leverages multi-view observations to comprehensively utilize LiDAR geometric information across extended spatial regions. Omni-LIVO introduces a Cross-View direct alignment strategy that maintains photometric consistency across non-overlapping views, and extends the Error-State Iterated Kalman Filter (ESIKF) with multi-view updates and adaptive covariance. The system is evaluated on public benchmarks and our custom dataset, showing improved accuracy and robustness over state-of-the-art LIVO, LIO, and visual-inertial SLAM baselines. Code and dataset will be released upon publication. △ Less

Submitted 29 March, 2026; v1 submitted 19 September, 2025; originally announced September 2025.

Comments: Accepted by IEEE Robotics and Automation Letters (RA-L). Early Access version available. This version supersedes all previous versions and is the official accepted manuscript for citation

BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots

Authors: Yufei Wei, Chenxiao Hu, Wangtao Lu, Sha Lu, Yuxiang Cui, Fuzhang Han, Rong Xiong, Yue Wang

Abstract: Scale-consistent ego-motion estimation is fundamental for autonomous ground robots. Bird's-Eye-View (BEV) representation naturally addresses the scale drift problem of monocular visual odometry (MVO) by providing a metric-scaled planar workspace, enabling the simplification of 6-DoF ego-motion to a more robust 3-DoF model. However, existing BEV-based methods suffer from two key limitations: sparse… ▽ More Scale-consistent ego-motion estimation is fundamental for autonomous ground robots. Bird's-Eye-View (BEV) representation naturally addresses the scale drift problem of monocular visual odometry (MVO) by providing a metric-scaled planar workspace, enabling the simplification of 6-DoF ego-motion to a more robust 3-DoF model. However, existing BEV-based methods suffer from two key limitations: sparse supervision signals from pose-only training, and information loss during perspective-to-BEV projection. We present BEV-ODOM2, an enhanced framework that addresses both limitations without requiring additional annotations. Our approach introduces (1) dense BEV optical flow supervision constructed directly from 3-DoF pose ground truth for pixel-level guidance, and (2) Perspective View (PV)-BEV fusion that computes correlation volumes before projection to preserve 6-DoF motion cues. An enhanced rotation sampling strategy further balances diverse motion patterns during training. We evaluate on four datasets with varied spatial scales: KITTI, Oxford, NCLT, and our newly collected ZJH-VO benchmark. BEV-ODOM2 achieves a 40\% RTE improvement over prior BEV-based methods, with real-time inference on an NVIDIA Jetson AGX Orin confirming edge deployment feasibility. The source code and the ZJH-VO dataset are publicly released to facilitate future research. △ Less

Submitted 2 June, 2026; v1 submitted 18 September, 2025; originally announced September 2025.

HiPhO: How Far Are (M)LLMs from Humans in the Latest High School Physics Olympiad Benchmark?

Authors: Fangchen Yu, Haiyuan Wan, Qianjia Cheng, Yuchen Zhang, Jiacheng Chen, Fujun Han, Yulun Wu, Junchi Yao, Ruilizhen Hu, Ning Ding, Yu Cheng, Tao Chen, Lei Bai, Dongzhan Zhou, Yun Luo, Ganqu Cui, Peng Ye

Abstract: Recently, the physical capabilities of (M)LLMs have garnered increasing attention. However, existing benchmarks for physics suffer from two major gaps: they neither provide systematic and up-to-date coverage of real-world physics competitions such as physics Olympiads, nor enable direct performance comparison with humans. To bridge these gaps, we present HiPhO, the first benchmark dedicated to hig… ▽ More Recently, the physical capabilities of (M)LLMs have garnered increasing attention. However, existing benchmarks for physics suffer from two major gaps: they neither provide systematic and up-to-date coverage of real-world physics competitions such as physics Olympiads, nor enable direct performance comparison with humans. To bridge these gaps, we present HiPhO, the first benchmark dedicated to high school physics Olympiads with human-aligned evaluation. Specifically, HiPhO highlights three key innovations. (1) Comprehensive Data: It compiles 13 latest Olympiad exams from 2024-2025, spanning both international and regional competitions, and covering mixed modalities that encompass problems spanning text-only to diagram-based. (2) Professional Evaluation: We adopt official marking schemes to perform fine-grained grading at both the answer and step level, fully aligned with human examiners to ensure high-quality and domain-specific evaluation. (3) Comparison with Human Contestants: We assign gold, silver, and bronze medals to models based on official medal thresholds, thereby enabling direct comparison between (M)LLMs and human contestants. Our large-scale evaluation of 30 state-of-the-art (M)LLMs shows that: across 13 exams, open-source MLLMs mostly remain at or below the bronze level; open-source LLMs show promising progress with multiple golds; closed-source reasoning MLLMs can achieve 6 to 12 gold medals; and most models still have a significant gap from full marks. These results highlight the performance gap between open-source models and top students, the strong reasoning abilities of closed-source models, and the remaining room for improvement. HiPhO, a human-aligned Olympiad benchmark for multimodal physical reasoning, is open-source at https://github.com/SciYu/HiPhO with a public leaderboard at https://phyarena.github.io/. △ Less

Submitted 19 September, 2025; v1 submitted 9 September, 2025; originally announced September 2025.

A new definition of peridynamic damage for thermo-mechanical fracture modeling

Authors: Sitong Tao, Fei Han

Abstract: A thermo-mechanical fracture modeling is proposed to address thermal failure issues, where the temperature field is calculated by a heat conduction model based on classical continuum mechanics (CCM), while the deformation field with discontinuities is calculated by the peridynamic (PD) model. The model is calculated by a CCM/PD alternating solution based on the finite element discretization, which… ▽ More A thermo-mechanical fracture modeling is proposed to address thermal failure issues, where the temperature field is calculated by a heat conduction model based on classical continuum mechanics (CCM), while the deformation field with discontinuities is calculated by the peridynamic (PD) model. The model is calculated by a CCM/PD alternating solution based on the finite element discretization, which ensures the calculation accuracy and facilitates engineering applications. The original PD model defines damage solely based on the number of broken bonds in the vicinity of the material point, neglecting the distribution of these bonds. To address this limitation, a new definition of the PD damage accounting for both the number of broken bonds and their specific distribution is proposed. As a result, damage in various directions can be captured, enabling more realistic thermal fracture simulations based on a unified mesh discretization. The effectiveness of the proposed model is validated by comparing numerical examples with analytical solutions. Moreover, simulation results of quasi-static and dynamic crack propagation demonstrate the model's ability to aid in understanding the initiation and propagation mechanisms of complex thermal fractures. △ Less

Submitted 31 August, 2025; originally announced September 2025.

Comments: 28 pages, 20 figures

U2UData+: A Scalable Swarm UAVs Autonomous Flight Dataset for Embodied Long-horizon Tasks

Authors: Tongtong Feng, Xin Wang, Feilin Han, Leping Zhang, Wenwu Zhu

Abstract: Swarm UAV autonomous flight for Embodied Long-Horizon (ELH) tasks is crucial for advancing the low-altitude economy. However, existing methods focus only on specific basic tasks due to dataset limitations, failing in real-world deployment for ELH tasks. ELH tasks are not mere concatenations of basic tasks, requiring handling long-term dependencies, maintaining embodied persistent states, and adapt… ▽ More Swarm UAV autonomous flight for Embodied Long-Horizon (ELH) tasks is crucial for advancing the low-altitude economy. However, existing methods focus only on specific basic tasks due to dataset limitations, failing in real-world deployment for ELH tasks. ELH tasks are not mere concatenations of basic tasks, requiring handling long-term dependencies, maintaining embodied persistent states, and adapting to dynamic goal shifts. This paper presents U2UData+, the first large-scale swarm UAV autonomous flight dataset for ELH tasks and the first scalable swarm UAV data online collection and algorithm closed-loop verification platform. The dataset is captured by 15 UAVs in autonomous collaborative flights for ELH tasks, comprising 12 scenes, 720 traces, 120 hours, 600 seconds per trajectory, 4.32M LiDAR frames, and 12.96M RGB frames. This dataset also includes brightness, temperature, humidity, smoke, and airflow values covering all flight routes. The platform supports the customization of simulators, UAVs, sensors, flight algorithms, formation modes, and ELH tasks. Through a visual control window, this platform allows users to collect customized datasets through one-click deployment online and to verify algorithms by closed-loop simulation. U2UData+ also introduces an ELH task for wildlife conservation and provides comprehensive benchmarks with 9 SOTA models. U2UData+ can be found at https://fengtt42.github.io/U2UData-2/. △ Less

Submitted 19 November, 2025; v1 submitted 25 August, 2025; originally announced September 2025.

Comments: Accepted by AAAI26

A fully-programmable integrated photonic processor for both domain-specific and general-purpose computing

Authors: Feng-Kai Han, Xiao-Yun Xu, Tian-Yu Zhang, Lei Feng, Chu-Han Wang, Jie Ma, Ze-Feng Lan, Chao-Qian Li, Yi Xie, Hai Yan, Yu-Fei Liu, Yu-Quan Peng, Xian-Min Jin

Abstract: A variety of complicated computational scenarios have made unprecedented demands on the computing power and energy efficiency of electronic computing systems, including solving intractable nondeterministic polynomial-time (NP)-complete problems and dealing with large-scale artificial intelligence models. Optical computing emerges as a promising paradigm to meet these challenges, whereas current op… ▽ More A variety of complicated computational scenarios have made unprecedented demands on the computing power and energy efficiency of electronic computing systems, including solving intractable nondeterministic polynomial-time (NP)-complete problems and dealing with large-scale artificial intelligence models. Optical computing emerges as a promising paradigm to meet these challenges, whereas current optical computing architectures have limited versatility. Their applications are usually either constrained to a specialized domain or restricted to general-purpose matrix computation. Here, we implement a fully-programmable integrated photonic processor that can be configured to tackle both specific computational problems and general-purpose matrix computation. We achieve complete end-to-end control of the photonic processor by utilizing a self-developed integrated programmable optoelectronic computing platform. For domain-specific computing, our photonic processor can efficiently solve two kinds of NP-complete problems: subset sum problem (far more than 2^N different instances) and exact cover problem. For general-purpose computation, we experimentally demonstrate high-precision optical dot product and further realize accurate image edge detection and MNIST handwritten image classification task with an accuracy of 97%. Our work enhances the versatility and capability of optical computing architecture, paving the way for its practical application in future high-performance and complex computing scenarios. △ Less

Submitted 19 August, 2025; originally announced August 2025.