Showing 1–50 of 582 results for author: Kong, D

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

Authors: Zhaoyi Li, Deyang Kong, Yuan Wei, Evan Yang, Ranran Shen, Mahardika Krisna Ihsani, Ming Yang, Wei Zhang, Chuan Hao, Jian Yang, Ran Tao, Bryan Dai, Shikun Zhang, Wei Ye, Ying Wei, Defu Lian

Abstract: On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly understood, as most studies evaluate OPD on a single domain and on benchmarks close to the training data. We present a controlled study that varies one generalization factor at a time, from in-domain distribution shifts to cro… ▽ More On-policy distillation (OPD) transfers teacher capabilities by supervising trajectories sampled from the student's own policy, yet its generalization behavior remains poorly understood, as most studies evaluate OPD on a single domain and on benchmarks close to the training data. We present a controlled study that varies one generalization factor at a time, from in-domain distribution shifts to cross-domain transfer and the multi-teacher setting. We find that OPD transfers a teacher's reasoning behavior rather than its answers to particular problems: training difficulty barely matters, and even problems the teacher never solves are useful. Transfer depends strongly on the origin relationship between teacher and student: same-origin pairs bring the student close to the teacher across languages, reasoning horizons, and even other domains, whereas cross-origin pairs mostly fit the trained distribution. This broad reach is a double-edged sword: since routing prompts to domain experts cannot confine each teacher's influence, combining them yields a mixture-dependent seesaw among their capabilities. These results clarify when OPD generalizes and offer a useful perspective for diagnosing multi-teacher OPD. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Comments: Under Review

Cyclops: LiDAR as a Camera That Dreams in Color

Authors: Wei Gao, Jian Shu, Mingle Zhao, Maani Ghaffari, David Kong, Chengzhong Xu, Hui Kong

Abstract: Conventionally, robotic perception relies heavily on cameras due to the rich semantic texture they provide. However, their performance degrades significantly in low-light or high-dynamic-range environments. Conversely, while Light Detection and Ranging (LiDAR) captures illumination-invariant geometric and intensity properties, the resulting data are typically single-channel and sparse, creating a… ▽ More Conventionally, robotic perception relies heavily on cameras due to the rich semantic texture they provide. However, their performance degrades significantly in low-light or high-dynamic-range environments. Conversely, while Light Detection and Ranging (LiDAR) captures illumination-invariant geometric and intensity properties, the resulting data are typically single-channel and sparse, creating a significant modality gap when applying vision models pre-trained on RGB datasets. In this paper, we propose Cyclops, a framework that translates sparse Non-Repetitive Scanning LiDAR (NRS-LiDAR) intensity into RGB video, enabling camera-free inference for all-day perception tasks. Our approach first converts sparse LiDAR intensity projections into dense representations via a frozen pre-trained densification module, serving as a geometrically rich source condition. The dense intensity latent is then transported toward the target RGB distribution through Latent Bridge Matching (LBM) with a learned velocity field in a few ODE integration steps. To mitigate inter-frame flickering, we inject prior-frame context via temporal attention layers and further formulate the velocity field as a policy optimized by a differentiable terminal reward that encourages terminal fidelity through backpropagation along the ODE trajectory. Extensive experiments demonstrate that the synthesized RGB, including those generated under near-dark conditions, enable standard RGB-based perception models to substantially outperform both LiDAR baselines and conventional cameras on semantic segmentation, lane detection, and point cloud colorization across diverse lighting conditions. △ Less

Submitted 17 August, 2026; originally announced August 2026.

Auditable agentic AI for evidence-grounded thyroid ultrasound diagnosis and reporting

Authors: Haifan Gong, Shiyu Chen, Bodong Wang, Yuqi Wang, Shijie Wang, Guoliang You, Xinyu Xiong, Haowei Wang, Mingzhi Mao, Dexing Kong, Qinghua Liu, Wei Lou, Fei Chen, Guanbin Li

Abstract: Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review. We present ThyroidXAgent, a clinician-interactive agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence reco… ▽ More Thyroid ultrasound diagnosis requires coordinated lesion localization, measurement, risk stratification and reporting, yet most AI systems address these tasks in isolation and provide limited support for clinical review. We present ThyroidXAgent, a clinician-interactive agentic AI system that coordinates specialized diagnostic tools and stores their outputs as an auditable case-level evidence record. The system was developed using OpenThyroidDB, a multicentre, multitask resource integrating approximately 0.3 million ultrasound images and 24,000 paired reports, and was evaluated on 28,458 non-overlapping test cases, including 8,721 cases from 35 centres in the private NHC-MISD-TUS cohort. Across heterogeneous datasets, ThyroidXAgent achieved a mean Dice score of 87.21 percent for nodule segmentation and a mean AUROC of 0.9466 for benign-malignant classification. The same workflow supported lymph-node metastasis prediction and follicular versus papillary thyroid carcinoma classification, with AUROCs of 0.864 and 0.805, respectively. For report generation, evidence-grounded assembly outperformed multimodal language-model baselines across three cohorts. ThyClinScore, a lesion-level clinical semantic metric introduced here, showed the strongest correlation with a location-aware language-model judge. ThyroidXAgent improved physician classification accuracy, increased report diagnostic consistency from 70.3 percent to 86.2 percent, and reduced segmentation and reporting time by 35.9 percent and 27.4 percent, respectively. These findings support auditable, clinician-correctable agentic AI for thyroid ultrasound diagnosis and reporting. △ Less

Submitted 12 August, 2026; originally announced August 2026.

Comments: Under review

Enhancing Social Intelligence in LLMs with Hierarchical Reasoning and Utterance-Level Goal Rewarding

Authors: Xiaofeng Wang, Kakam Chong, Shuai Xiao, DeXin Kong, Qingyuan Tian, Chen Ju, Xu Yan, Shuai Zhao, Fei Huang, Rui Wang, Shuguang Han, jufeng chen

Abstract: Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination and rapid adaptation. Current methods often apply uniform goal-based rewards to every utterance, overlooking the specificity of objectives at each dialogue turn and failing to account for the rationale of potential strategies. Inspired by the Theo… ▽ More Large language models (LLMs) excel in structured tasks but struggle with dynamic social interactions, where success requires long-term goal coordination and rapid adaptation. Current methods often apply uniform goal-based rewards to every utterance, overlooking the specificity of objectives at each dialogue turn and failing to account for the rationale of potential strategies. Inspired by the Theory of Planned Behavior, we propose the Think-Strategy-Response (TSR) framework, which decomposes social dialogue into two hierarchical stages: high-level strategic planning and low-level linguistic execution. To optimize TSR, we introduce Linearized Hierarchical Reinforcement Learning with Variance-Gated Rewards (LHRL-VGR), a novel algorithm that dynamically routes rewards - balancing goal completion and strategy adherence - based on the variance of goal achievement scores. Experiments on the SOTOPIA benchmark show that our approach fine-tunes a Qwen2.5-7B agent to surpass the GPT-4o baseline by 7.32% in goal completion success, demonstrating state-of-the-art performance in multi-agent social negotiation tasks. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Equipment-centric workpiece localization in near real-time using deep learning-based vision and event-driven finite state machines

Authors: Dohyeon Kong, Jaebong Cho, Hyunbo Cho

Abstract: Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of extreme temperatures, surface degradation, and irregular routing. This study presents an equipment-centric framework that infers workpiece locations from handling equipment observed by multiple static 2D cameras. The framework estimates floorplan-spa… ▽ More Continuous workpiece localization is essential for traceability and process coordination in hot forging, but direct tracking is unreliable because of extreme temperatures, surface degradation, and irregular routing. This study presents an equipment-centric framework that infers workpiece locations from handling equipment observed by multiple static 2D cameras. The framework estimates floorplan-space 3D equipment coordinates and recognizes grasp and release activities. Event-driven finite state machines validate these activities as discrete handling events and continuously update workpiece states and locations. A keypoint-guided attention mechanism integrated into a 3D convolutional neural network improves activity recognition by focusing on functionally relevant equipment regions. Evaluation in an operational hot forging factory achieved 100\% event detection accuracy within a 33-second tolerance window, a mean localization error of 317.8 mm, and a mean system latency of 21 seconds. The framework connects vision-based perception with interpretable event-driven reasoning and supports visualization of workpiece transfers and quantitative analysis of equipment operations. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Comments: 21 pages, 14 figures, 9 tables. Published in The International Journal of Advanced Manufacturing Technology

Journal ref: Int J Adv Manuf Technol 142, 635-655 (2026)

Qwen-CUA: Native Computer Use for (almost) Everything

Authors: Dunjie Lu, Shuai Bai, Tianyi Bai, Sicheng Fan, Chang Gao, Jian Guan, Feng Hu, Mianqiu Huang, Xingyang Huang, Yizhen Jiang, Yuheng Jing, Dehui Kong, Ning Li, Dayiheng Liu, Shixuan Liu, Zheng Liu, Que Shen, Bowen Wang, Junli Wang, Chencan Wu, Rui Xie, Tianbao Xie, Zhihui Xie, Haiyang Xu, An Yang , et al. (21 additional authors not shown)

Abstract: Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and m… ▽ More Native computer use offers a general interface for agents to operate almost any software available to people, but requires long-horizon state tracking, large-scale interactive experience, and learning from sparse yet verifiable outcomes. We introduce Qwen-CUA, a native computer-use agent with a 397B-A17B Qwen mixture-of-experts backbone. It observes only screenshots and acts through keyboard and mouse events, without DOM trees, accessibility metadata, or task-specific APIs. Its scaffold maintains up to 20 active screenshots and folds older visual history in fixed-size blocks to retain recent evidence while preserving reusable prompt prefixes. For training, we build a cloud rollout fleet with access to nearly 100,000 vCPUs and tens of thousands of concurrent environments, construct approximately 40,000 verifiable tasks, and collect personalized long-horizon workflows across everyday and professional software. We optimize complete trajectories with verifiable rewards and trajectory slicing, while iterative training runs refresh supervised data and recalibrate reinforcement-learning tasks. Across eight benchmarks, Qwen-CUA outperforms Qwen3.7 and remains competitive with leading proprietary systems, reaching 86.2 on OSWorld-Verified and 18.5/48.4 binary/partial completion on OSWorld 2.0. Scaling the same recipe to a model with over one trillion parameters yields Qwen-CUA-Max, improving these scores to 87.6 and 21.2/53.3. Qwen-CUA also reduces RedTeamCUA attack success from 36.6 to 16.4 relative to Qwen3.7. Efficiency analyses, a browser deployment, and Bash-augmented experiments further characterize practical behavior. These results establish native computer use as a broadly capable agent foundation and highlight scalable verifiable interaction and hybrid tool use as key directions. △ Less

Submitted 3 August, 2026; originally announced August 2026.

Comments: 24 pages, 10 figures. Technical report

Before Agents Speak: Pre-hoc Failure Risk Inference in Multi-Agent Systems

Authors: Shi Lin, Chenpei Wang, Peng Qian, Dezhang Kong, Minghao Li, Yufeng Li, Xun Wang

Abstract: LLM-based multi-agent systems (MAS) have exhibited remarkable capabilities in collaborative reasoning and decision-making, yet their interconnected communications introduce new systemic risk: localized hallucinations can propagate along agent communication chain, amplify through interactions, and ultimately trigger cascading failures. Existing countermeasures predominantly follow a post-hoc paradi… ▽ More LLM-based multi-agent systems (MAS) have exhibited remarkable capabilities in collaborative reasoning and decision-making, yet their interconnected communications introduce new systemic risk: localized hallucinations can propagate along agent communication chain, amplify through interactions, and ultimately trigger cascading failures. Existing countermeasures predominantly follow a post-hoc paradigm, identifying failures only after unsafe behaviors emerge, by which time harmful effects may have already spread throughout the agent network. To tackle this problem, we investigate a complementary pre-hoc approach and propose HalluProp, a Propagation-aware Hallucination inference framework that estimates individual agent failures and emergent system-level hallucination risks before inter-agent interaction. First, we model intrinsic hallucination risks by identifying fine-grained semantic misalignment between agent roles and task queries. We then characterize inter-agent risk propagation by modeling both semantic influence and communication topology. Finally, we integrate these two risks via a differentiable Noisy-OR inference mechanism to derive a systemic diagnosis. Extensive experiments show that HalluProp accurately localizes faulty agents, achieving an average AUROC of 84.6%, while enabling sub-second diagnosis with over $65\times$ speedup over post-hoc methods. By facilitating early intervention through upstream screening, HalluProp effectively complements post-hoc methods, highlighting the potential of pre-hoc risk inference for building more reliable multi-agent systems. △ Less

Submitted 29 July, 2026; originally announced July 2026.

Forecasting Trajectory-Level Safety Risks in Black-Box Multi-Turn Interactions

Authors: Shi Lin, Peng Qian, Dinghao Liu, Renjie Sun, Sifan Wu, Dezhang Kong, Chenpei Wang, Xun Wang

Abstract: As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories. In multi-turn interactions, malicious intent can be decomposed across seemingly harmless turns and gradually reconstructed through interaction trajectories, eventu… ▽ More As large language models (LLMs) evolve from standalone assistants into autonomous agents, ensuring their safety requires shifting beyond pointwise risk assessment to understand how risks emerge and unfold over long-horizon trajectories. In multi-turn interactions, malicious intent can be decomposed across seemingly harmless turns and gradually reconstructed through interaction trajectories, eventually resulting in safety failures. Existing safeguards remain largely reactive, detecting manifested violations while lacking the ability to predict latent risk evolution and enable preemptive prevention. To address this limitation, we propose Recast, a safety risk forecasting framework that advances LLM safeguarding beyond turn-level violation detection to trajectory-level risk prediction. Recast first retrieves risk-relevant evidence from both short-term dialogue progression and long-term historical context via a dual-scale trajectory view. It then models compositional risk evolution by capturing the current risk configuration and its temporal dynamics. Finally, a causal temporal encoder learns latent risk evolution patterns and predicts the distribution of future risk emergence turns. Extensive experiments across 7 risk categories show that Recast predicts 88.3% of future safety failures with an average lead time of 2.41 turns, while maintaining a false alarm rate of 12.3%, showcasing the effectiveness of trajectory-level forecasting in identifying emerging risks before safety violations occur. △ Less

Submitted 29 July, 2026; originally announced July 2026.

PRISM-Net: Patient-specific reference-guided inter-breast symmetry matching for three-class breast DCE-MRI classification

Authors: Boya Zhang, Shuaiwen Zhou, Di Kong, Mingxu Wang, Wenbiao Du, Yiman Zhong, Yuexin Duan, Xiawei Yue, Liuquan Cheng, Xiru Li

Abstract: Breast DCE-MRI AI is increasingly being explored for breast-level classification of no-lesion, benign, and malignant findings, beyond conventional lesion-centered diagnosis. Within this broader diagnostic scope, however, patient-specific background variability remains a major source of imaging confounding across classification tasks. Existing approaches predominantly focus on unilateral or lesion-… ▽ More Breast DCE-MRI AI is increasingly being explored for breast-level classification of no-lesion, benign, and malignant findings, beyond conventional lesion-centered diagnosis. Within this broader diagnostic scope, however, patient-specific background variability remains a major source of imaging confounding across classification tasks. Existing approaches predominantly focus on unilateral or lesion-centric analysis, whereas bilateral methods offer limited explicit modeling of spatially adaptive cross-breast correspondence. We propose PRISM-Net, a registration-free bilateral framework that leverages contralateral breast features as patient-specific references for background-aware representation learning. PRISM-Net integrates bilateral feature matching and asymmetry-aware attention to establish adaptive inter-breast correspondence and enhance representations of discriminative asymmetric patterns. On ODELIA, Macro AUC, Micro AUC, and quadratic weighted kappa were $84.11 \pm 2.33$, $90.64 \pm 1.61$, and $60.94 \pm 5.64$ on the in-distribution test set, and $68.51 \pm 4.54$, $80.74 \pm 2.68$, and $43.45 \pm 7.10$ on the held-out institution, respectively, outperforming the evaluated baseline methods across the primary evaluation metrics. PRISM-Net further demonstrated performance on independent institutional and background-complexity evaluations. Ablation experiments revealed that both bilateral relation modeling and asymmetry-aware reweighting contributed to improved classification performance. These findings highlight patient-specific bilateral reference modeling as a clinically grounded strategy for DCE-MRI interpretation, improving asymmetric pattern discrimination through explicit modeling of background complexity. △ Less

Submitted 7 August, 2026; v1 submitted 29 July, 2026; originally announced July 2026.

Comments: 15 pages, 7 figures, 5 tables

Observations of a Solar Jet Triggered by Reconnection between Super-penumbral Fibrils and a Mini-filament

Authors: Liheng Yang, Xiaoli Yan, Qingmin Zhang, Zhike Xue, Zhe Xu, Jincheng Wang, Fangyu Xu, Yian Zhou, Defang Kong, Weijie Meng, Xinsheng Zhang, Qiaoling Li, Liping Yang

Abstract: Coronal jets are highly dynamic phenomena in the solar atmosphere, yet their driving mechanisms remain an active topic of investigation. In this paper, we report a coronal jet triggered by the interaction between super-penumbral fibrils and a mini-filament, based on coordinated observations from the New Vacuum Solar Telescope (NVST), the Chinese H$α$ Solar Explorer (CHASE), and the Solar Dynamics… ▽ More Coronal jets are highly dynamic phenomena in the solar atmosphere, yet their driving mechanisms remain an active topic of investigation. In this paper, we report a coronal jet triggered by the interaction between super-penumbral fibrils and a mini-filament, based on coordinated observations from the New Vacuum Solar Telescope (NVST), the Chinese H$α$ Solar Explorer (CHASE), and the Solar Dynamics Observatory (SDO). The fibrils were anchored between the negative-polarity region of a sunspot and an emerging positive-polarity region associated with a moving magnetic feature (MMF). As the positive polarity migrated outward, the fibrils elongated and interacted with the mini-filament, one of whose footpoints was rooted in pre-existing negative-polarity fields. Intense brightenings at the interaction site, together with changes in the connectivity of the mini-filament footpoint from the pre-existing negative polarity to the sunspot, indicate the occurrence of magnetic reconnection. The event produced a narrow hot jet accompanied by a broader cool component. The cool plasma exhibited a clockwise rotation, providing evidence for the transfer of magnetic twist during reconnection. Persistent magnetic flux cancellation was observed before and during the jet eruption. These observations demonstrate that small-scale magnetic structures, such as MMFs, can significantly influence mini-filament eruptions and highlight the important role of flux cancellation in triggering coronal jet activity. △ Less

Submitted 28 July, 2026; originally announced July 2026.

Comments: 18 pages, 8 figures, accepted by ApJ

VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers

Authors: Xianghong Fang, Yuan Yuan, Dehan Kong, Tim G. J. Rudner

Abstract: Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requires significant computational resources which, in practice, all but prevents the development of novel, cutting-edge VQ techniques under resource constraints. To address this limitation, we propose {\bf VQ-Transplant}, a simple framework that enabl… ▽ More Vector Quantization (VQ) underpins modern discrete visual tokenization. However, training quantization modules for state-of-the-art VQ-based models requires significant computational resources which, in practice, all but prevents the development of novel, cutting-edge VQ techniques under resource constraints. To address this limitation, we propose {\bf VQ-Transplant}, a simple framework that enables plug-and-play integration of new VQ modules into frozen, pre-trained tokenizers by replacing their native VQ modules. Crucially, the proposed transplantation process preserves all encoder-decoder parameters, obviating the need for costly end-to-end retraining when modifying the quantization method. To mitigate decoder-quantization mismatch, we introduce a lightweight decoder adaptation strategy (trained for only 5 epochs on ImageNet-1k) to align feature priors with the new quantization space. In our empirical evaluation, we find that VQ-Transplant allows obtaining near state-of-the-art reconstruction fidelity for industry-level models like VAR while reducing the training cost by 95\%. VQ-Transplant democratizes quantization research by enabling resource-efficient integration of novel VQ techniques while matching industry-level reconstruction performance. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Comments: 20 pages, 9 figures and 16 tables

Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation

Authors: Liqian Feng, Lintao Wang, Xiaochen Liu, Anusha Withana, Ken-Tye Yong, Dehui Kong, Zhiyong Wang, Kun Hu

Abstract: Most sign language translation (SLT) methods focus on isolated native sign-spoken pairs (e.g., American Sign Language - English). Extending language-specific SLT models to multilingual translation would improve accessibility by enabling communication across diverse sign and spoken language communities. However, existing multilingual SLT approaches still struggle to learn a unified model that minim… ▽ More Most sign language translation (SLT) methods focus on isolated native sign-spoken pairs (e.g., American Sign Language - English). Extending language-specific SLT models to multilingual translation would improve accessibility by enabling communication across diverse sign and spoken language communities. However, existing multilingual SLT approaches still struggle to learn a unified model that minimizes cross-lingual conflicts while capturing shared cross-lingual semantics and preserving language-specific variations across different sign languages. Therefore, we propose Q-BridgeNet, a unified framework for multilingual SLT that jointly mitigates cross-lingual conflicts across both the sign language and spoken language sides. On the sign language side, Q-BridgeNet learns discrete Q-units via adaptive segmentation and residual vector quantization: a shared base codebook provides language-agnostic semantic primitives, while language-specific residual codebooks refine heterogeneous signing semantics. On the spoken language side, a multilingual LLM is fine-tuned to operate in the Q-unit space, leveraging cross-lingual priors to enable a unified SLT model. Experiments on PHOENIX14T, How2Sign, and CSL-Daily show that Q-BridgeNet effectively mitigates cross-lingual conflicts, achieving state-of-the-art performance on native sign-spoken pairs while also demonstrating strong generalization to non-native pairs. Our source code is publicly available at: https://github.com/FengLiQ/Q-BridgeNet △ Less

Submitted 13 July, 2026; originally announced July 2026.

Enhanced two-photon sources in a cavity-coupled two-atom system

Authors: Zhicai Chen, Jun Xu, Deyi Kong, Xiangming Hu, Fei Wang

Abstract: We propose a component-selective scheme for improving two-photon sources in a cavity-coupled two-atom system, where a single cavity mode interacts with two two-level atoms driven by phase-controlled classical fields of the same frequency. By controlling the atomic detunings and driving phase, the system can be tailored toward optimized cavity-field two-photon blockade or strongly correlated fluore… ▽ More We propose a component-selective scheme for improving two-photon sources in a cavity-coupled two-atom system, where a single cavity mode interacts with two two-level atoms driven by phase-controlled classical fields of the same frequency. By controlling the atomic detunings and driving phase, the system can be tailored toward optimized cavity-field two-photon blockade or strongly correlated fluorescence photon-pair emission. When the two-cavity-photon component is enhanced, the cavity field exhibits optimized two-photon blockade with simultaneous suppression of unwanted one- and three-photon components at a comparable two-photon population. In another parameter regime, strongly correlated fluorescence photon pairs can also be generated from the two atoms by selecting the double-atomic-excitation component in the same two-excitation manifold. This approach provides a route toward high-quality and versatile two-photon sources, with potential applications in few-photon quantum optics and quantum information processing. △ Less

Submitted 7 July, 2026; originally announced July 2026.

Comments: 11 pages,7 figures

Chiral interaction enhanced magnon bundle emission

Authors: Zhicai Chen, Deyi Kong, Chengdeng Gou, Xiangming Hu, Fei Wang

Abstract: In this paper, we suggest a chiral interaction scheme to enhance magnon bundle emission by placing a qubit and a magnon into a cascaded-cavity setup, respectively. It is found that the unidirectional interaction prolongs the lifetime of the target excited state, thereby suppressing the magnon re-excitation and promoting both the average purity and number of two-magnon bundles. Consequently, the ch… ▽ More In this paper, we suggest a chiral interaction scheme to enhance magnon bundle emission by placing a qubit and a magnon into a cascaded-cavity setup, respectively. It is found that the unidirectional interaction prolongs the lifetime of the target excited state, thereby suppressing the magnon re-excitation and promoting both the average purity and number of two-magnon bundles. Consequently, the chiral interaction not only offers directional control but also improves the quality of the multi-magnon source, which may find potential applications in quantum information processing. △ Less

Submitted 1 July, 2026; originally announced July 2026.

Comments: Accepted by Physical Review A

Journal ref: Phys. Rev. A 114, 013710 (2026)

OSOR: One-Step Diffusion Inpainting for Effect-Aware Object Removal

Authors: Qinming Zhou, Chenxi Sun, Deyang Kong, Junhao He, Xiangheng Tang, Peike Yu, Haotian Wu, Leilei Cao, Linfeng Zhang

Abstract: Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which are difficult to model, and the fact that user-provided masks are often inaccurate or incomplete. With billions of parameters and tens of denoising steps, diffusion-based models achieve strong removal performance at the expense of substantial computati… ▽ More Real-world object removal is challenging due to two key difficulties: the target object's non-local effects, such as shadows and reflections, which are difficult to model, and the fact that user-provided masks are often inaccurate or incomplete. With billions of parameters and tens of denoising steps, diffusion-based models achieve strong removal performance at the expense of substantial computational cost, limiting their use in interactive applications and on edge devices. To address these challenges, we present OSOR (One-Step Object Removal), which simultaneously achieves efficient, effect-aware, and mask-robust object removal. Concretely, OSOR introduces: (1) an occupancy-guided discriminator for precise boundary supervision, enabling stable single-step diffusion training; (2) an alpha head that leverages knowledge from pretrained diffusion models to predict appropriate removal regions with minimal overhead, thereby handling imperfect masks; and (3) a semantic-anchored verification pipeline (SAVP) that filters noisy instruction-based triplets to produce effect-aware supervision at scale. Using SAVP, we curate CORNE, which contains 280K verified removal pairs, and further annotate AnimeEraseBench and TextEraseBench to evaluate performance on more complex removal tasks. Experiments show that OSOR surpasses strong multi-step diffusion baselines in perceptual quality while achieving $4\times$ to $30\times$ faster inference. △ Less

Submitted 26 June, 2026; originally announced June 2026.

Comments: Code and resources are available at https://github.com/Zhouqm-Git/osor

AgentDSE: Reasoning-Augmented Architectural Design Space Exploration

Authors: Chenyu Wang, Jiahe Caroline Shi, David Kong, Duane S. Boning, Zishen Wan, Yilun Du, Vijay Janapa Reddi

Abstract: Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods. This inefficiency arises because conventional methods treat the simulator as a black-box oracle. In contrast, human architects effectively guide exploration by reasoning through physical constraints, performance bottlene… ▽ More Traditional architectural design space exploration (DSE) is highly inefficient, typically requiring tens of thousands of simulator evaluations across various optimization methods. This inefficiency arises because conventional methods treat the simulator as a black-box oracle. In contrast, human architects effectively guide exploration by reasoning through physical constraints, performance bottlenecks, data reuse, and workload structures. To bridge this gap, we introduce AgentDSE, a simulator-in-the-loop methodology driven by a general-purpose large language model (LLM) coding agent. AgentDSE automates this architectural-reasoning loop without requiring model fine-tuning, precomputed design databases, or domain-specific optimizer code. Across deep neural network (DNN) accelerator mapping, hardware/software co-design, and CPU cache-hierarchy optimization, AgentDSE achieves competitive or better design quality with up to two orders of magnitude fewer evaluations. AgentDSE also produces inspectable traces that surface architectural hypotheses, performance cliffs, implicit priors, and simulator artifacts, making every search decision traceable rather than buried in optimizer state. △ Less

Submitted 19 June, 2026; originally announced June 2026.

Comments: Accepted to the Machine Learning for Architecture and Systems Workshop (MLArchSys), co-located with ISCA 2026

ParkingTransformer: LLM-Enhanced End-to-End Trajectory Planning for Autonomous Parking

Authors: Hauteng Wu, Xu Li, Dong Kong, Zihang Wang, Xieyuanli Chen, Benwu Wang, Wenkai Zhu

Abstract: End-to-end autonomous parking has emerged as a critical task within the realm of autonomous driving. However, existing methods suffer from black-box characteristics, lacking high-level semantic understanding and interpretability, which impedes the realization of seamless long-distance autonomous parking from the road to the target spot. To address these limitations, we propose ParkingTransformer,… ▽ More End-to-end autonomous parking has emerged as a critical task within the realm of autonomous driving. However, existing methods suffer from black-box characteristics, lacking high-level semantic understanding and interpretability, which impedes the realization of seamless long-distance autonomous parking from the road to the target spot. To address these limitations, we propose ParkingTransformer, a novel framework that leverages multi-view perception and the scene understanding capability of Large Language Models (LLMs). By combining trajectory queries with LLMs implicit state features, our method interacts directly with historical information and raw sensor data to output planning trajectories, eliminating the need for dense Bird's-View (BEV) representations. To compensate for the inadequate spatial reasoning ability of LLMs, we introduce 3D positional encoding to explicitly inject spatial geometric awareness. Furthermore, a fixed-window streaming mechanism is designed for historical information processing, significantly improving long-term temporal processing efficiency and inference speed. Additionally, a coarse-to-fine decoding strategy is employed to progressively enhance trajectory precision. Extensive closed-loop experiments are conducted on the CARLA simulator and real-world vehicle platforms. The results demonstrate that our method achieves a driving score of 61.32 in CARLA simulator and an average success rate of 88.70% in real-world experiments, validating the feasibility and effectiveness of the proposed algorithms. △ Less

Submitted 12 June, 2026; originally announced June 2026.

VEPHand: View-Efficient Photometric Hand Performance Capture at Scale

Authors: Zhengyang Shen, Kai-Hung Chang, Erroll Wood, Deying Kong, Bo Peng, Timo Bolkart, Jinlong Yang, Bowen Zhao, Danhang Tang, Sasa Petrovic, Emre Aksan, Jérémy Riviere, Vassilis Choutas, Delio Vicini, Jay Busch, Shichen Liu, Zhe Cao, Hugh Liu, JingJing Shen, Jonathan Taylor, Mingsong Dou

Abstract: Robust, high-fidelity 3D hand capture, while fundamental to digital human creation, remains challenging with practical multi-view systems that balance rich photometry with the geometric ambiguities of reconstruction arising from limited viewpoint density. This paper presents an end-to-end pipeline for dynamic hand performance capture and registration, specifically designed for view-efficient setup… ▽ More Robust, high-fidelity 3D hand capture, while fundamental to digital human creation, remains challenging with practical multi-view systems that balance rich photometry with the geometric ambiguities of reconstruction arising from limited viewpoint density. This paper presents an end-to-end pipeline for dynamic hand performance capture and registration, specifically designed for view-efficient setups ($\sim$20 views). We address key challenges with two primary innovations. First, to overcome reconstruction difficulties like limited view overlap and background clutter, our mask-free neural method robustly extracts detailed hand geometry and appearance from unmasked images using scene parameterization and scenario-specific density regularization. Second, addressing registration challenges such as accurately capturing non-linear skin deformations and ensuring plausible results during severe self-contact, we propose a physics-inspired framework. It aligns reconstructions to a personalized hand model by optimizing intrinsic volumetric offsets within its canonical tetrahedral mesh, alongside pose parameters. This approach, supported by robust losses and optimization, captures fine surface deformations, ensures plausible results under severe articulation and self-contact, and demonstrates strong tolerance to input noise. We demonstrate the scalability and robustness of our automated pipeline on an extensive dataset of over 12,000 sequences, from which we also derive a large-scale, high-quality synthetic 2D/3D hand dataset for training downstream tasks. This showcases its effectiveness for single hands, intricate two-hand interactions, and natural hand-object manipulations. Our method achieves state-of-the-art reconstruction fidelity in view-efficient, unmasked scenarios and highly accurate registration. Our project page are available at https://vephand.github.io/. △ Less

Submitted 18 June, 2026; v1 submitted 14 June, 2026; originally announced June 2026.

ACM Class: I.3.8; I.4.5

High-Fidelity 4D Hand-Object Capture via Multi-View Spatiotemporal Tracking and Physics-Aware Gaussians

Authors: Bo Peng, Xu Chen, Yi Gu, Hidenobu Matsuki, Mingsong Dou, Jingjing Shen, Deying Kong, Juyong Zhang, Zhengyang Shen

Abstract: The growing demand for high-fidelity 4D hand-object interaction (HOI) data in embodied AI and spatial computing is currently bottlenecked by the reliance on pre-scanned object templates and physical markers. While recent methods have demonstrated promising results in reconstructing 4D hand-object interaction from videos, they are highly sensitive to initial estimates of hand and object poses. Yet,… ▽ More The growing demand for high-fidelity 4D hand-object interaction (HOI) data in embodied AI and spatial computing is currently bottlenecked by the reliance on pre-scanned object templates and physical markers. While recent methods have demonstrated promising results in reconstructing 4D hand-object interaction from videos, they are highly sensitive to initial estimates of hand and object poses. Yet, estimating these poses from images is challenging, in particular under severe occlusion which is inherent in hand-object interaction scenarios. We propose a novel system for the robust and accurate reconstruction of hands and objects from synchronized and calibrated multi-view videos without requiring any templates or markers. Our system consists of two main components with key innovations: (1) a multi-view feed-forward transformer model that aggregates cross-view geometry and temporal cues to provide a reliable, metric-consistent initialization for both poses and dense object geometry, and (2) a hand-object physics-aware Gaussian-based optimization framework to refine the initial estimates, integrating tetrahedral constraints, collision refinement, and appearance decomposition to produce physically plausible and visually accurate reconstruction. Validated on public benchmarks and an extensive internal dataset, our pipeline achieves highly robust, artifact-free reconstruction, providing an efficient foundation for automated 4D asset generation. Our project page are available at https://zyshen021.github.io/HOSTPG/. △ Less

Submitted 18 June, 2026; v1 submitted 14 June, 2026; originally announced June 2026.

Comments: Project page: https://hostpg.github.io/

SALT: When More Rollouts Don't Help in Group-Based Policy Optimization and How to Make Them Matter

Authors: Powei Chang, Jinpeng Zhang, Chaoqun Sun, MiniWell Tsao, Lianrui Li, Jianxiang Xiang, Chenyu Wang, Yukang Gao, Dongying Kong

Abstract: Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals. However, merely increasing the number of rollouts does not reliably strengthen learning: under GRPO-style group normalization, per-rollout policy-gradient features can concentrate into a low-rank, signed geometry, caus… ▽ More Reinforcement learning with verifiable rewards (RLVR) often adopts GRPO-style group-relative updates, sampling multiple rollouts per prompt to construct normalized learning signals. However, merely increasing the number of rollouts does not reliably strengthen learning: under GRPO-style group normalization, per-rollout policy-gradient features can concentrate into a low-rank, signed geometry, causing substantial cancellation during aggregation and weakening the effective update. We address this failure mode with SALT, a Subspace-Adaptive geometry pLug-in componenT that uses sample-wise gradient geometry to reweight the coefficients of group-relative updates. SALT estimates a dominant shared subspace from the mini-batch Gram geometry, decomposes group-relative coefficients into shared and residual channels, and adaptively amplifies the residual channel when signed cancellation is severe. Across diverse reasoning-oriented RLVR benchmarks and model scales, SALT improves effective update geometry and performance without modifying the reward model or the rollout sampling procedure △ Less

Submitted 4 June, 2026; originally announced June 2026.

ShotCrop$^3$: Cropping Human-Centric Images into Cinematic Triple-Shot Compositions

Authors: Dehong Kong, Lina Lei, Lingtao Zheng, Chenyang Wu, Ailing Zhang, Xinran Qin, Teng Ma, Jiaqi Xu, Zhixin Wang, Zhikai Chen, Xuecheng Qi, Renjing Pei, Fan Li

Abstract: Prior work on aesthetic composition typically produces a single aesthetically pleasing crop, overlooking the narrative value of composing multiple shots from one scene. In practice, multi-shot composition is critical for downstream creative workflows: commercial posters often require multiple crops with different emphases (e.g., context, subject, and emotion/product details) to present key story b… ▽ More Prior work on aesthetic composition typically produces a single aesthetically pleasing crop, overlooking the narrative value of composing multiple shots from one scene. In practice, multi-shot composition is critical for downstream creative workflows: commercial posters often require multiple crops with different emphases (e.g., context, subject, and emotion/product details) to present key story beats. Therefore, we propose \textbf{Triple-Shot Compositions (TSC)}, a composition task that generates a three-shot set -- establishing, medium, and close-up -- from a single human-centric image, each paired with a brief shot description to support visual narration. To learn TSC with limited expert annotations, we introduce \textbf{ShotCrop} which undergoes a three-stage training process: it first applies Chain-of-Thought supervised fine-tuning to establish basic reasoning and aesthetic shot-cropping skills, then performs semi-supervised fine-tuning with high-confidence pseudo labels to further enhance aesthetic capability, and is finally optimized with Group Relative Policy Optimization for \textbf{ShotCrop} (GRPO-S) using a composite reward tailored for it. Specifically, our pseudo-labeling strategy combines MLLM-based scoring, aesthetic assessment, and CLIP similarity to retain high-confidence training signals. In addition, we present TSC-Bench, a benchmark of 1.2k expert-annotated test cases. Notably, ShotCrop achieves an average improvement of \textbf{2.82} times over GPT-5 in shot localization accuracy. △ Less

Submitted 3 June, 2026; originally announced June 2026.

DSA: Dynamic Step Allocation for Fast Autoregressive Video Generation

Authors: Thanh-Tung Le, Yunhan Zhao, Menglei Chai, Zhengyang Shen, Zhe Cao, Danhang Tang, Xiaohui Xie, Deying Kong

Abstract: Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation frameworks produce autoregressive video diffusion models with reduced latency, yet these models still use a fixed number of denoising steps per frame, wasting computation on predictable frames and under-refining challen… ▽ More Video diffusion transformers have achieved state-of-the-art visual quality, but their high inference cost remains a major bottleneck for real-time applications. Recent distillation frameworks produce autoregressive video diffusion models with reduced latency, yet these models still use a fixed number of denoising steps per frame, wasting computation on predictable frames and under-refining challenging ones. We present DSA, a confidence-guided adaptive computation framework for AR video diffusion. DSA introduces a lightweight confidence head, trained jointly with the generator under a distribution-matching distillation objective, to estimate per-frame denoising reliability. At inference, this confidence signal dynamically adjusts the number of diffusion steps: simple frames terminate early for speed, while complex frames receive additional refinement. Our method requires no extra video data, no heuristics, and little architectural modification. Experiments show that DSA achieves real-time autoregressive video generation, reaching 22.63 FPS with sub-second latency on H100 GPUs, while maintaining competitive or superior VBench quality compared to recent autoregressive and bidirectional video diffusion models. Our results demonstrate that confidence-guided adaptive sampling provides an effective and practical path toward interactive video generation. △ Less

Submitted 3 June, 2026; originally announced June 2026.

Comments: CVPR2026, Findings Track

Perceive Before Reasoning: A Pre-Reasoning Perception Framework for Efficient and Reliable Proactive Mobile Agents

Authors: Zhijie Ding, Weinan Hong, Zicheng Zhu, Lei Li, Dezhi Kong, Hao Wang, Peng Zhou, Xuchu Jiang, Jiaming Xu

Abstract: Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide \emph{when} to intervene before determining \emph{how} to assist. Existing systems often implement these two decisions within a unified MLLM-based pipeline, leading to goal misalignment between conservative intervention filtering and com… ▽ More Multimodal large language models (MLLMs) have substantially advanced mobile agents, yet proactive mobile assistance remains challenging because agents must decide \emph{when} to intervene before determining \emph{how} to assist. Existing systems often implement these two decisions within a unified MLLM-based pipeline, leading to goal misalignment between conservative intervention filtering and comprehensive assistance generation, as well as redundant inference when the agent should remain silent. To address these limitations, we propose the \textbf{Pre-Reasoning Perception Framework (PRPF)}, a two-stage framework built on perceiving before reasoning. PRPF introduces a lightweight Multimodal Proactive Perceptor (MPP) for intervention gating and context compression, and activates the Proactive Agent Reasoner (PAR) only when intervention is warranted. Experiments on the ProactiveMobile benchmark show that PRPF substantially reduces false trigger rates (FTR) while improving success rates (SR) and inference efficiency over the ProactiveMobile baseline. △ Less

Submitted 2 June, 2026; originally announced June 2026.

Gravothermal Collapse: Robust Against Baryonic Feedback

Authors: Demao Kong, Hai-Bo Yu

Abstract: We perform a stress test of gravothermal collapse in self-interacting dark matter (SIDM) halos under baryonic feedback using a semi-analytical oscillating-potential model in controlled N-body simulations. For high-concentration halos, where the SIDM thermalization timescale is short, gravothermal collapse is only mildly delayed and never stalled, even under extremely strong feedback. In contrast,… ▽ More We perform a stress test of gravothermal collapse in self-interacting dark matter (SIDM) halos under baryonic feedback using a semi-analytical oscillating-potential model in controlled N-body simulations. For high-concentration halos, where the SIDM thermalization timescale is short, gravothermal collapse is only mildly delayed and never stalled, even under extremely strong feedback. In contrast, the collapse of a median-concentration halo can be significantly delayed, but it resumes once feedback ceases. The final density profile of such halos depends sensitively on the episodic feedback history, producing a broad diversity in central densities. These results strengthen the interpretation of dense compact perturbers identified in recent strong-lensing observations as core-collapsed SIDM halos. △ Less

Submitted 29 May, 2026; originally announced May 2026.

Comments: 5 pages, 3 figures

Physics-Aware 3D Gaussian Editing for Driving Scene Generation

Authors: Feng Zhou, Jian Zhang, Yuhang Sun, He Wang, Qiong Wen, Debao Kong, Tieru Wu, Rui Ma

Abstract: 3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing methods have limited support for road geometry editing (e.g., inserting speed humps or sunken roads), and generally do not couple such edits with plausible vehicle-road interaction d… ▽ More 3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing methods have limited support for road geometry editing (e.g., inserting speed humps or sunken roads), and generally do not couple such edits with plausible vehicle-road interaction dynamics. Such editing is essential for generating training data under extreme driving scenarios or evaluating system reliability under these road irregularities. Moreover, many optimization-based methods require minutes of per-edit refinement, while existing efficient alternatives mainly focus on appearance-level or object-level manipulation rather than physics-aware road irregularity editing. To address these limitations, we propose RoVES, a Road-and-Vehicle Editing System for physics-aware 3D Gaussian editing in driving scenes. RoVES enables single-image-driven road geometry insertion and couples the edited road profile with a 4-DOF half-car vehicle dynamics model to achieve physics-aware vehicle pose correction in vertical displacement and pitch. RoVES inserts road elements in a one-shot, optimization-free pipeline (1.84s), and the full pipeline (including color transfer and vehicle-dynamics-based pose correction) completes in 6.24s; it edits dynamic vehicles via pose editing and corrects poses frame-by-frame to approximate dynamics-consistent vertical displacement and pitch responses. Experiments on the Waymo dataset show that RoVES provides practical efficiency and competitive visual consistency for physics-aware driving scene generation. △ Less

Submitted 24 May, 2026; originally announced May 2026.

Echo: Learning from Experience Data via User-Driven Refinement

Authors: Hande Dong, Xiaoyun Liang, Jiarui Yu, Jiayi Lin, Changqing Ai, Feng Liu, Wenjun Zhang, Rongbi Wei, Chaofan Zhu, Linjie Che, Feng Wu, Xin Shen, Dexu Kong, Xiaotian Wang, Qiuyuan Chen, Bingxu An, Yueting Lei, Qiang Lin

Abstract: Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend these barriers. Today, the widespread deployment of AI agents grants us low-cost access to massive streams of such real-world experience. However, raw interactio… ▽ More Static "human data" faces inherent limitations: it is expensive to scale and bounded by the knowledge of its creators. Continuous learning from "experience data" - interactions between agents and their environments - promises to transcend these barriers. Today, the widespread deployment of AI agents grants us low-cost access to massive streams of such real-world experience. However, raw interaction logs are inherently noisy, filled with trial-and-error and low information density, rendering them inefficient for direct model training. We introduce Echo, a generalized framework designed to operationalize the transition from raw experience to learnable knowledge, effectively "echoing" environmental feedback back into the training loop for model optimization. In today's agent ecosystem, user refinement serves as a primary source of such feedback: driven by responsibility for the outcome, users rigorously transform flawed agent proposals into verified solutions. These user-driven refinement sequences inherently distill agents' crude attempts into high-quality training signals. Echo systematically harvests these signals to continuously align the agent with real-world needs. Large-scale validation in a production code completion environment confirms that Echo effectively harnesses this pipeline, breaking the static performance ceiling by increasing the acceptance rate from 25.7% to 35.7%. △ Less

Submitted 21 May, 2026; originally announced May 2026.

Finite-Time Analysis of MCTS in Continuous POMDP Planning

Authors: Da Kong, Vadim Indelman

Abstract: This paper presents a finite-time analysis for Monte Carlo Tree Search (MCTS) in Partially Observable Markov Decision Processes (POMDPs), with probabilistic concentration bounds in both discrete and continuous observation spaces. While MCTS-style solvers such as POMCP achieve empirical success in many applications, rigorous finite-time guarantees remain an open problem due to the nonstationarity a… ▽ More This paper presents a finite-time analysis for Monte Carlo Tree Search (MCTS) in Partially Observable Markov Decision Processes (POMDPs), with probabilistic concentration bounds in both discrete and continuous observation spaces. While MCTS-style solvers such as POMCP achieve empirical success in many applications, rigorous finite-time guarantees remain an open problem due to the nonstationarity and the interdependencies induced by heuristic action selection (e.g., UCB). In the discrete setting, we address these challenges by extending the polynomial exploration bonus to UCB in POMDP setting, yielding polynomial concentration bounds for the empirical value estimation at the root node. For continuous observation spaces, we introduce an abstract partitioning framework and propose a finite-time bound on partitioning loss. Under mild conditions, we prove highprobability bound on value estimates in POMDPs with continuous observation space. Specifically, we propose Voro-POMCPOW, a variant of POMCPOW with f inite-time guarantees that adaptively partitions the continuous observation space using Voronoi cells. This approach maintains a finite branching factor while preserving the original observation generator. Empirical validation demonstrates that the proposed Voro-POMCPOW shows competitive performance while providing theoretical guarantees. Although our analysis focuses on continuous POMDPs, the techniques developed herein are also applicable to continuous MDPs, closing another gap on the MDP side. △ Less

Submitted 8 May, 2026; originally announced May 2026.

Comments: 9 pages, 1 figure

YOSE: You Only Select Essential Tokens for Efficient DiT-based Video Object Removal

Authors: Chenyang Wu, Lina Lei, Fan Li, Chun-Le Guo, Dehong Kong, Xinran Qin, Zhixin Wang, Ming-Ming Cheng, Chongyi Li

Abstract: Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from substantial inference latency. For instance, although MiniMax Remover achieves state-of-the-art visual quality, it operates at only around 10FPS, primarily due to dense computations over the entire spatiotemporal token s… ▽ More Recent advances in Diffusion Transformer (DiT)-based video generation technologies have shown impressive results for video object removal. However, these methods still suffer from substantial inference latency. For instance, although MiniMax Remover achieves state-of-the-art visual quality, it operates at only around 10FPS, primarily due to dense computations over the entire spatiotemporal token space, even when only a small masked region actually requires processing. In this paper, we present YOSE, You Only Select Essential Tokens, an efficient fine-tuning framework. YOSE introduces two key components: Batch Variable-length Indexing (BVI) and Diffusion Process Simulator (DiffSim) Module. BVI is a differentiable dynamic indexing operator that adaptively selects essential tokens based on mask information, enabling variable-length token processing across samples. DiffSim provides a diffusion process approximation mechanism for unmasked tokens, which simulates the influence of unmasked regions within DiT self-attention to maintain semantic consistency for masked tokens. With these designs, YOSE achieves mask-aware acceleration, where the inference time scales approximately linearly with the masked regions, in contrast to full-token diffusion methods whose computation remains constant regardless of the mask size. Extensive experiments demonstrate that YOSE achieves up to 2.5X speedup in 70% of cases while maintaining visual quality comparable to the baseline. Code is available at: https://github.com/Wucy0519/YOSE-CVPR26. △ Less

Submitted 29 April, 2026; originally announced April 2026.

Comments: accepted by CVPR2026

Probing Coronal Activity Using Radio Signals Based on the 2021 superior conjunction of Mars: the Downlink Data from Tianwen-1

Authors: Yu-Chen Liu, De-Qing Kong, Song Tan, Zi-Han Zhao, Zan Wang, Dong-Hao Liu, Xin-Ying Zhu, Yan Su, Hong-Bo Zhang

Abstract: During the first superior conjunction of the Tianwen-1 Mars probe in October 2021, its downlink signal received by the Wuqing 70-m radio telescope passed within 4.53 solar radii of the Sun. The signal was significantly perturbed by the solar wind, providing a mechanism to probe coronal activity. We analyze the Doppler frequency scintillation spectrum of the solar wind within 10 solar radii to deri… ▽ More During the first superior conjunction of the Tianwen-1 Mars probe in October 2021, its downlink signal received by the Wuqing 70-m radio telescope passed within 4.53 solar radii of the Sun. The signal was significantly perturbed by the solar wind, providing a mechanism to probe coronal activity. We analyze the Doppler frequency scintillation spectrum of the solar wind within 10 solar radii to derive a characteristic frequency scintillation parameter. Statistical analysis indicates this parameter increases as the signal path approaches the Sun, with notable anomalies observed on October 5, 13, and 15. Comparisons with SOHO and SDO data reveal strong spatio-temporal correlations between these scintillation anomalies and coronal activity. We demonstrate that this parameter effectively identifies solar phenomena, including coronal streamers, high-speed solar wind, and coronal mass ejections (CMEs). Quantitative analysis confirms a distinct temporal correlation and delay between frequency scintillation and solar wind speed changes, validating the feasibility of spatially localizing solar activity. △ Less

Submitted 15 April, 2026; originally announced April 2026.

High-efficiency graphene-silicon slot-waveguide microring modulator at 1.5 μm and 2 μm wavelength bands

Authors: Chao Luan, Deming Kong, Yong Liu, Yunhong Ding, Hao Hu

Abstract: Electro-optic (E/O) modulators are crucial for optical communication but face a trade-off between modulation bandwidth and efficiency. A small footprint could reduce the capacitance and increase the bandwidth, however, this usually results in a low modulation efficiency. Here, we present an integrated E/O modulator that simultaneously achieves wideband large bandwidth and high modu- lation efficie… ▽ More Electro-optic (E/O) modulators are crucial for optical communication but face a trade-off between modulation bandwidth and efficiency. A small footprint could reduce the capacitance and increase the bandwidth, however, this usually results in a low modulation efficiency. Here, we present an integrated E/O modulator that simultaneously achieves wideband large bandwidth and high modu- lation efficiency operation by embedding a partially overlapped double-layer graphene on a compact silicon slot waveguide microring resonator. At 1550 nm, the graphene-silicon slot-waveguide demon- strates a high phase modulation efficiency of Vπ L = 220 V μm, and the corresponding microring modulator has a large bandwidth of over 70 GHz, a compact active length of 10 μm, and an optical modulation amplitude (OMA) of -1.97 dBm under a 3-V voltage swing. The modulator operates at a data rate of 50 Gbit/s with an open eye diagram under a 2-V Vpp RF drive voltage. The graphene modulator operation is broadband, and we also characterize its performance at 2 μm wavelength band. At 2 μm wavelength band, the microring modulator has a large bandwidth of over 20 GHz, an OMA of -3.36 dBm under a 6-V voltage swing, and an open eye diagram at 20 Gbit/s with a 2-V Vpp RF drive voltage. The difference in performance is caused by the bandwidth limit of the 2 μm wavelength band measurement setup. The broadband, large bandwidth, compact, highly effi- cient, and energy efficient graphene E/O modulator has the potential to enable large-scale graphene photonic integrated circuits, facilitating a broad range of applications such as optical interconnects, optical neural networks, and programmable photonic circuits. △ Less

Submitted 9 April, 2026; originally announced April 2026.

Comments: arXiv admin note: text overlap with arXiv:2604.03153

AttnDiff: Attention-based Differential Fingerprinting for Large Language Models

Authors: Haobo Zhang, Zhenhua Xu, Junxian Li, Shangfeng Sheng, Dezhang Kong, Meng Han

Abstract: Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering operations such as fine-tuning (including PPO/DPO), pruning/compression, and model merging. We propose \textsc{AttnDiff}, a data-efficient white-box framework that extracts fingerprints from models via intrinsic informa… ▽ More Protecting the intellectual property of open-weight large language models (LLMs) requires verifying whether a suspect model is derived from a victim model despite common laundering operations such as fine-tuning (including PPO/DPO), pruning/compression, and model merging. We propose \textsc{AttnDiff}, a data-efficient white-box framework that extracts fingerprints from models via intrinsic information-routing behavior. \textsc{AttnDiff} probes minimally edited prompt pairs that induce controlled semantic conflicts, captures differential attention patterns, summarizes them with compact spectral descriptors, and compares models using CKA. Across Llama-2/3 and Qwen2.5 (3B--14B) and additional open-source families, it yields high similarity for related derivatives while separating unrelated model families (e.g., $>0.98$ vs.\ $<0.22$ with $M=60$ probes). With 5--60 multi-domain probes, it supports practical provenance verification and accountability. △ Less

Submitted 7 April, 2026; originally announced April 2026.

Comments: Accepted at ACL2026 Main

MPTF-Net: Multi-view Pyramid Transformer Fusion Network for LiDAR-based Place Recognition

Authors: Shuyuan Li, Zihang Wang, Xieyuanli Chen, Wenkai Zhu, Xiaoteng Fang, Peizhou Ni, Junhao Yang, Dong Kong

Abstract: LiDAR-based place recognition (LPR) is essential for global localization and loop-closure detection in large-scale SLAM systems. Existing methods typically construct global descriptors from Range Images or BEV representations for matching. BEV is widely adopted due to its explicit 2D spatial layout encoding and efficient retrieval. However, conventional BEV representations rely on simple statistic… ▽ More LiDAR-based place recognition (LPR) is essential for global localization and loop-closure detection in large-scale SLAM systems. Existing methods typically construct global descriptors from Range Images or BEV representations for matching. BEV is widely adopted due to its explicit 2D spatial layout encoding and efficient retrieval. However, conventional BEV representations rely on simple statistical aggregation, which fails to capture fine-grained geometric structures, leading to performance degradation in complex or repetitive environments. To address this, we propose MPTF-Net, a novel multi-view multi-scale pyramid Transformer fusion network. Our core contribution is a multi-channel NDT-based BEV encoding that explicitly models local geometric complexity and intensity distributions via Normal Distribution Transform, providing a noise-resilient structural prior. To effectively integrate these features, we develop a customized pyramid Transformer module that captures cross-view interactive correlations between Range Image Views (RIV) and NDT-BEV at multiple spatial scales. Extensive experiments on the nuScenes, KITTI and NCLT datasets demonstrate that MPTF-Net achieves state-of-the-art performance, specifically attaining a Recall@1 of 96.31\% on the nuScenes Boston split while maintaining an inference latency of only 10.02 ms, making it highly suitable for real-time autonomous unmanned systems. △ Less

Submitted 6 April, 2026; originally announced April 2026.

Wideband integrated high-speed graphene-silicon slot-waveguide electro-absorption modulator at 2 μm and 1.5 μm wavebands

Authors: Chao Luan, Deming Kong, Yunhong Ding, Hao Hu

Abstract: The 2-μm waveband, emerging as a highly promising candidate for optical communication, offers an extended wavelength window for high-speed optical transmission. Despite its potential, the development of integrated electro-optic (E/O) modulators operating at this wavelength range has been limited. Such E/O modulators are crucial for high-speed optical communication systems at the 2-μm waveband. In… ▽ More The 2-μm waveband, emerging as a highly promising candidate for optical communication, offers an extended wavelength window for high-speed optical transmission. Despite its potential, the development of integrated electro-optic (E/O) modulators operating at this wavelength range has been limited. Such E/O modulators are crucial for high-speed optical communication systems at the 2-μm waveband. In this work, we propose and experimentally demonstrate high-performance E/O absorption modulators based on a graphene-silicon slot waveguide. Our approach enables wideband, high-speed, efficient, robust and compact modulators at both 2-μm and 1.5-μm wavebands. This work represents a significant advancement towards the realization of high-speed integrated E/O modulators for optical communication systems operating at the 2-μm wavelength range. △ Less

Submitted 3 April, 2026; originally announced April 2026.

Open-loop POMDP Simplification and Safe Skipping of Replanning with Formal Performance Guarantees

Authors: Da Kong, Vadim Indelman

Abstract: Partially Observable Markov Decision Processes (POMDPs) provide a principled mathematical framework for decision-making under uncertainty. However, the exact solution to POMDPs is computationally intractable. In this paper, we address the computational intractability by introducing a novel framework for adaptive open-loop simplification with formal performance guarantees. Our method adaptively int… ▽ More Partially Observable Markov Decision Processes (POMDPs) provide a principled mathematical framework for decision-making under uncertainty. However, the exact solution to POMDPs is computationally intractable. In this paper, we address the computational intractability by introducing a novel framework for adaptive open-loop simplification with formal performance guarantees. Our method adaptively interleaves open-loop and closed-loop planning via a topology-based belief tree, enabling a significant reduction in planning complexity. The key contribution lies in the derivation of efficiently computable bounds which provide formal guarantees and can be used to ensure that our simplification can identify the immediate optimal action of the original POMDP problem. Our framework therefore provides computationally tractable performance guarantees for macro-actions within POMDPs. Furthermore, we propose a novel framework for safely skipping replanning during execution, supported by theoretical guarantees on multi-step open-loop action sequences. To the best of our knowledge, this framework is the first to address skipping replanning with formal performance guarantees. Practical online solvers for our proposed simplification are developed, including a sampling-based solver and an anytime solver. Empirical results demonstrate substantial computational speedups while maintaining provable performance guarantees, advancing the tractability and efficiency of POMDP planning. △ Less

Submitted 1 April, 2026; originally announced April 2026.

Comments: 18 pages, 5 figures. Accepted to WAFR 2026

A Possible Mechanism to Explain the Prograde Equatorial Jet of a Jupiter-like Gaseous Giant

Authors: Yuchen Lian, Pengshuo Duan, Dali Kong

Abstract: Gaseous giants are characterized by their deep atmospheres, which lack clear boundaries with their interiors; therefore, their internal states could directly influence atmospheric dynamics. So far, most modeling studies have considered deep convection as the primary mechanism by which the interior influences atmospheric dynamics. In this work, we propose another possible mechanism that might cruci… ▽ More Gaseous giants are characterized by their deep atmospheres, which lack clear boundaries with their interiors; therefore, their internal states could directly influence atmospheric dynamics. So far, most modeling studies have considered deep convection as the primary mechanism by which the interior influences atmospheric dynamics. In this work, we propose another possible mechanism that might crucially determine the appearance of gaseous giants' atmospheric cloud-top jet winds, tracing them to a typical hydromagnetic wave (the so-called equatorial Magnetic-Archimedes-Coriolis wave) generated within the stably stratified, strongly magnetized helium rain layer. The associated thermal perturbations can propagate upward through the convective molecular hydrogen envelope, eventually affecting the atmospheric thermal structure - the zonal inhomogeneities that are conducive to the formation of the eastward atmospheric equatorial jet (super-rotation). Our results have important implications for understanding the equatorial dynamics of gaseous giants. This mechanism could also help explain the equatorial westward jets (sub-rotation) observed on Uranus and Neptune, which lack the helium rain layers. △ Less

Submitted 29 March, 2026; originally announced March 2026.

GaussianPile: A Unified Sparse Gaussian Splatting Framework for Slice-based Volumetric Reconstruction

Authors: Di Kong, Yikai Wang, Wenjie Guo, Yifan Bu, Boya Zhang, Yuexin Duan, Xiawei Yue, Wenbiao Du, Yiman Zhong, Yuwen Chen, Cheng Ma

Abstract: Slice-based volumetric imaging is widely applied and it demands representations that compress aggressively while preserving internal structure for analysis. We introduce GaussianPile, unifying 3D Gaussian splatting with an imaging system-aware focus model to address this challenge. Our proposed method introduces three key innovations: (i) a slice-aware piling strategy that positions anisotropic 3D… ▽ More Slice-based volumetric imaging is widely applied and it demands representations that compress aggressively while preserving internal structure for analysis. We introduce GaussianPile, unifying 3D Gaussian splatting with an imaging system-aware focus model to address this challenge. Our proposed method introduces three key innovations: (i) a slice-aware piling strategy that positions anisotropic 3D Gaussians to model through-slice contributions, (ii) a differentiable projection operator that encodes the finite-thickness point spread function of the imaging acquisition system, and (iii) a compact encoding and joint optimization pipeline that simultaneously reconstructs and compresses the Gaussian sets. Our CUDA-based design retains the compression and real-time rendering efficiency of Gaussian primitives while preserving high-frequency internal volumetric detail. Experiments on microscopy and ultrasound datasets demonstrate that our method reduces storage and reconstruction cost, sustains diagnostic fidelity, and enables fast 2D visualization, along with 3D voxelization. In practice, it delivers high-quality results in as few as 3 minutes, up to 11x faster than NeRF-based approaches, and achieves consistent 16x compression over voxel grids, offering a practical path to deployable compression and exploration of slice-based volumetric datasets. △ Less

Submitted 20 March, 2026; originally announced March 2026.

Comments: Accepted by IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026 (CVPR 2026)

CoEmpaTeam: Enhancing Cognitive Empathy using LLM-based Avatars and Dynamic Role Play in Virtual Reality

Authors: Dehui Kong, Martin Feick, Shi Liu, Alexander Maedche

Abstract: Cognitive empathy, the ability to understand others' perspectives, is essential for effective communication, reducing biases, and constructive negotiation. However, this skill is declining in a performance-driven society, which prioritizes efficiency over perspective-taking. Here, the training of cognitive empathy is challenging because it is a subtle, hard-to-perceive soft skill. To address this,… ▽ More Cognitive empathy, the ability to understand others' perspectives, is essential for effective communication, reducing biases, and constructive negotiation. However, this skill is declining in a performance-driven society, which prioritizes efficiency over perspective-taking. Here, the training of cognitive empathy is challenging because it is a subtle, hard-to-perceive soft skill. To address this, we developed CoEmpaTeam, a VR-based system that enables users to train their cognitive empathy by using LLM-driven avatars with different personalities. Through dynamic role play, users actively engage in perspective-taking, experiencing situations through another person's eyes. CoEmpaTeam deploys three avatars who significantly differ in their personality, validated by a technical evaluation and an online experiment (n=90). Next, we evaluated the system through a lab experiment with 32 participants who performed three sessions across two weeks, followed by a one-week diary study. Our results showed a significant increase in cognitive empathy, which, according to participants, transferred into their real lives. △ Less

Submitted 17 March, 2026; originally announced March 2026.

Comments: Accepted to appear in the Proceedings of the ACM CHI Conference on Human Factors in Computing Systems (CHI 2026)

LR-SGS: Robust LiDAR-Reflectance-Guided Salient Gaussian Splatting for Self-Driving Scene Reconstruction

Authors: ZY Chen, F Zhu, H Zhu, DY Kong, XK Kuang, YJ Zhang, CM Jiang

Abstract: Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only for Gaussian initialization or depth supervision, while the rich scene information contained in point clouds, such as reflectance, and the complementarity between LiDAR and RGB hav… ▽ More Recent 3D Gaussian Splatting (3DGS) methods have demonstrated the feasibility of self-driving scene reconstruction and novel view synthesis. However, most existing methods either rely solely on cameras or use LiDAR only for Gaussian initialization or depth supervision, while the rich scene information contained in point clouds, such as reflectance, and the complementarity between LiDAR and RGB have not been fully exploited, leading to degradation in challenging self-driving scenes, such as those with high ego-motion and complex lighting. To address these issues, we propose a robust and efficient LiDAR-reflectance-guided Salient Gaussian Splatting method (LR-SGS) for self-driving scenes, which introduces a structure-aware Salient Gaussian representation, initialized from geometric and reflectance feature points extracted from LiDAR and refined through a salient transform and improved density control to capture edge and planar structures. Furthermore, we calibrate LiDAR intensity into reflectance and attach it to each Gaussian as a lighting-invariant material channel, jointly aligned with RGB to enforce boundary consistency. Extensive experiments on the Waymo Open Dataset demonstrate that LR-SGS achieves superior reconstruction performance with fewer Gaussians and shorter training time. In particular, on Complex Lighting scenes, our method surpasses OmniRe by 1.18 dB PSNR. △ Less

Submitted 26 May, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

Comments: 8 pages, 7 figures

RIE-Greedy: Regularization-Induced Exploration for Contextual Bandits

Authors: Tong Li, Thiago de Queiroz Casanova, Eric M. Schwartz, Victor Kostyuk, Dehan Kong, Joseph J. Williams

Abstract: Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. However, it is difficult to directly apply simple and effective exploration strategies--such as Thompson Sampling or UCB--on top of those black-box estimators. Existing approaches rely on sophisticated assumptions or intractable procedures that are hard to ver… ▽ More Real-world contextual bandit problems with complex reward models are often tackled with iteratively trained models, such as boosting trees. However, it is difficult to directly apply simple and effective exploration strategies--such as Thompson Sampling or UCB--on top of those black-box estimators. Existing approaches rely on sophisticated assumptions or intractable procedures that are hard to verify and implement in practice. In this work, we explore the use of an exploration-free (pure-greedy) action selection strategy, that exploits the randomness inherent in model fitting process as an intrinsic source of exploration. More specifically, we note that the stochasticity in cross-validation based regularization process can naturally induce Thompson Sampling-like exploration. We show that this regularization-induced exploration is theoretically equivalent to Thompson Sampling in the two-armed bandit case and empirically leads to reliable exploration in large-scale business environments compared to benchmark methods such as epsilon-greedy and other state-of-the-art approaches. Overall, our work reveals how regularized estimator training itself can induce effective exploration, offering both theoretical insight and practical guidance for contextual bandit design. △ Less

Submitted 17 May, 2026; v1 submitted 11 March, 2026; originally announced March 2026.

A Statistically Reliable Optimization Framework for Bandit Experiments in Scientific Discovery

Authors: Tong Li, Travis Mandel, Goldie Phillips, Anna Rafferty, Eric M. Schwartz, Dehan Kong, Joseph J. Williams

Abstract: Scientific experimentation is largely driven by statistical hypothesis testing to determine significant differences in interventions. Traditionally, experimenters allocate samples uniformly between each intervention. However, such an approach may lead to suboptimal outcomes - multi-armed bandits (MABs) addresses this problem by allocating samples adaptively to maximize outcomes. Yet, two challenge… ▽ More Scientific experimentation is largely driven by statistical hypothesis testing to determine significant differences in interventions. Traditionally, experimenters allocate samples uniformly between each intervention. However, such an approach may lead to suboptimal outcomes - multi-armed bandits (MABs) addresses this problem by allocating samples adaptively to maximize outcomes. Yet, two challenges have hindered the use of MABs in scientific domains. First, common hypothesis tests (e.g., $t$-tests) become invalid under adaptive sampling without correction, leading to inflated type~I and type~II errors. This is an understudied problem, and prior solutions suffer from issues such as low statistical power which prevent adoption in many practical settings. Second, practitioners must explicitly balance cumulative reward with statistical efficiency, yet no general methodology exists to quantify this trade-off across algorithms. In this paper, we study assumption modification and critical region correction approaches for hypothesis testing that enable common tests to be applied to adaptively collected data. We provide heuristic justification for its power efficiency and show in simulation that it achieves higher power than existing approaches. Further, we derive a theoretically and practically motivated objective function for adaptive experiment evaluation, which we integrate into a unified experimental framework. Our framework asks experimenters to specify an experiment extension cost for their problem, and based on that enables our proposed optimization procedure to select the bandit algorithm that best balances reward and power in their setting. We show that our approach enables practitioners to improve outcomes with only slightly more steps than uniform randomization, while retaining statistical validity. △ Less

Submitted 16 March, 2026; v1 submitted 11 March, 2026; originally announced March 2026.

WebChain: A Large-Scale Human-Annotated Dataset of Real-World Web Interaction Traces

Authors: Sicheng Fan, Rui Wan, Yifei Leng, Gaoning Liang, Li Ling, Yanyi Shang, Dehan Kong

Abstract: We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core Triple Alignment of visual, structural, and action data to provide rich, multi-modal supervision. The data is collected via a scalable pipeline that ensures coverag… ▽ More We introduce WebChain, the largest open-source dataset of human-annotated trajectories on real-world websites, designed to accelerate reproducible research in web agents. It contains 31,725 trajectories and 318k steps, featuring a core Triple Alignment of visual, structural, and action data to provide rich, multi-modal supervision. The data is collected via a scalable pipeline that ensures coverage of complex, high-value tasks often missed by synthetic methods. Leveraging this dataset, we propose a Dual Mid-Training recipe that decouples spatial grounding from planning, achieving state-of-the-art performance on our proposed WebChainBench and other public GUI benchmarks. Our work provides the data and insights necessary to build and rigorously evaluate the next generation of scalable web agents. △ Less

Submitted 14 April, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

WebFactory: Automated Compression of Foundational Language Intelligence into Grounded Web Agents

Authors: Sicheng Fan, Qingyun Shi, Shengze Xu, Shengbo Cai, Tieyong Zeng, Li Ling, Yanyi Shang, Dehan Kong

Abstract: Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a more critical factor: the efficiency of compressing a large language model's (LLM) latent knowledge into actionable agent behavior. We introduce WebFactory, a… ▽ More Current paradigms for training GUI agents are fundamentally limited by a reliance on either unsafe, non-reproducible live web interactions or costly, scarce human-crafted data and environments. We argue this focus on data volume overlooks a more critical factor: the efficiency of compressing a large language model's (LLM) latent knowledge into actionable agent behavior. We introduce WebFactory, a novel, fully automated closed-loop reinforcement learning pipeline for GUI agents, systematically compressing LLM-encoded internet intelligence into efficient, grounded actions. Our pipeline features a process of scalable environment synthesis, knowledge-aware task generation, LLM-powered trajectory collection, decomposed reward RL training, and systematic agent evaluation. Remarkably, our agent demonstrates exceptional data efficiency and generalization. Trained on synthetic data from only 10 websites within WebFactory, it achieves performance comparable to GUI agents trained on the same amount of human-annotated data from a much larger set of environments. This superior performance is consistent across our internal offline and online transfer benchmarks, where our agent also significantly outperforms the base foundation model. We further provide critical insights into the "embodiment potential" of different LLM foundations, offering a new axis for model evaluation. This work presents a scalable and cost-effective paradigm for transforming passive internet knowledge into active, grounded intelligence, marking a critical step towards general-purpose interactive agents. △ Less

Submitted 14 April, 2026; v1 submitted 5 March, 2026; originally announced March 2026.

Constraint-Aware Generative Re-ranking for Multi-Objective Optimization in Advertising Feeds

Authors: Chenfei Li, Hantao Zhao, Weixi Yao, Ruiming Huang, Rongrong Lu, Geng Tian, Dongying Kong

Abstract: Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization via autoregressive decoding, but their deployment is hindered by high inference latency and limited constraint handling. We propose a constraint-aware generativ… ▽ More Optimizing reranking in advertising feeds is a constrained combinatorial problem, requiring simultaneous maximization of platform revenue and preservation of user experience. Recent generative ranking methods enable listwise optimization via autoregressive decoding, but their deployment is hindered by high inference latency and limited constraint handling. We propose a constraint-aware generative reranking framework that transforms constrained optimization into bounded neural decoding. Unlike prior approaches that separate generator and evaluator models, our framework unifies sequence generation and reward estimation into a single network. We further introduce constraint-aware reward pruning, integrating constraint satisfaction directly into decoding to efficiently generate optimal sequences. Experiments on large-scale industrial feeds and online A/B tests show that our method improves revenue and user engagement while meeting strict latency requirements, providing an efficient neural solution for constrained listwise optimization. △ Less

Submitted 4 March, 2026; originally announced March 2026.

Comments: 14 pages, 2 figures, 3 tables

Wild-Drive: Off-Road Scene Captioning and Path Planning via Robust Multi-modal Routing and Efficient Large Language Model

Authors: Zihang Wang, Xu Li, Benwu Wang, Wenkai Zhu, Xieyuanli Chen, Dong Kong, Kailin Lyu, Yinan Du, Yiming Peng, Haoyang Che

Abstract: Explainability and transparent decision-making are essential for the safe deployment of autonomous driving systems. Scene captioning summarizes environmental conditions and risk factors in natural language, improving transparency, safety, and human--robot interaction. However, most existing approaches target structured urban scenarios; in off-road environments, they are vulnerable to single-modali… ▽ More Explainability and transparent decision-making are essential for the safe deployment of autonomous driving systems. Scene captioning summarizes environmental conditions and risk factors in natural language, improving transparency, safety, and human--robot interaction. However, most existing approaches target structured urban scenarios; in off-road environments, they are vulnerable to single-modality degradations caused by rain, fog, snow, and darkness, and they lack a unified framework that jointly models structured scene captioning and path planning. To bridge this gap, we propose Wild-Drive, an efficient framework for off-road scene captioning and path planning. Wild-Drive adopts modern multimodal encoders and introduces a task-conditioned modality-routing bridge, MoRo-Former, to adaptively aggregate reliable information under degraded sensing. It then integrates an efficient large language model (LLM), together with a planning token and a gate recurrent unit (GRU) decoder, to generate structured captions and predict future trajectories. We also build the OR-C2P Benchmark, which covers structured off-road scene captioning and path planning under diverse sensor corruption conditions. Experiments on OR-C2P dataset and a self-collected dataset show that Wild-Drive outperforms prior LLM-based methods and remains more stable under degraded sensing. The code and benchmark will be publicly available at https://github.com/wangzihanggg/Wild-Drive. △ Less

Submitted 28 February, 2026; originally announced March 2026.

ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices

Authors: Dezhi Kong, Zhengzhao Feng, Qiliang Liang, Hao Wang, Haofei Sun, Changpeng Yang, Yang Li, Peng Zhou, Shuai Nie, Hongzhen Wang, Linfeng Zhou, Hao Jia, Jiaming Xu, Runyu Shi, Ying Huang

Abstract: Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging paradigm of proactive intelligence, where agents autonomously anticipate needs and initiate actions, represents the next frontier for mobile agents. However, its… ▽ More Multimodal large language models (MLLMs) have made significant progress in mobile agent development, yet their capabilities are predominantly confined to a reactive paradigm, where they merely execute explicit user commands. The emerging paradigm of proactive intelligence, where agents autonomously anticipate needs and initiate actions, represents the next frontier for mobile agents. However, its development is critically bottlenecked by the lack of benchmarks that can address real-world complexity and enable objective, executable evaluation. To overcome these challenges, we introduce ProactiveMobile, a comprehensive benchmark designed to systematically advance research in this domain. ProactiveMobile formalizes the proactive task as inferring latent user intent across four dimensions of on-device contextual signals and generating an executable function sequence from a comprehensive function pool of 63 APIs. The benchmark features over 3,660 instances of 14 scenarios that embrace real-world complexity through multi-answer annotations. To ensure quality, a team of 30 experts conducts a final audit of the benchmark, verifying factual accuracy, logical consistency, and action feasibility, and correcting any non-compliant entries. Extensive experiments demonstrate that our fine-tuned Qwen2.5-VL-7B-Instruct achieves a success rate of 19.15%, outperforming o1 (15.71%) and GPT-5 (7.39%). This result indicates that proactivity is a critical competency widely lacking in current MLLMs, yet it is learnable, emphasizing the importance of the proposed benchmark for proactivity evaluation. △ Less

Submitted 8 May, 2026; v1 submitted 25 February, 2026; originally announced February 2026.

Retarded Stellar Dynamo in Tidally Deformed M Dwarfs

Authors: Song Wang, Wenbo Li, Henggeng Han, Dali Kong, Jifeng Liu, Xinlin Zhao

Abstract: Current studies of stellar dynamos primarily focus on spherical stars, leaving their behavior in distorted stars largely unexplored. We utilize stars of varying distortions to examine the relation between stellar cycle periods ($P_{\rm cyc}$) and rotational periods ($P_{\rm rot}$), which are closely linked to dynamo processes. By analyzing a sample of tidally distorted M dwarfs in cataclysmic vari… ▽ More Current studies of stellar dynamos primarily focus on spherical stars, leaving their behavior in distorted stars largely unexplored. We utilize stars of varying distortions to examine the relation between stellar cycle periods ($P_{\rm cyc}$) and rotational periods ($P_{\rm rot}$), which are closely linked to dynamo processes. By analyzing a sample of tidally distorted M dwarfs in cataclysmic variables, we identify an anti-correlation between $P_{\rm cyc}$ and $P_{\rm rot}$, in contrast to the lack of such a relation in single M dwarfs. This means that stars with greater deformation have longer cycle periods, suggesting variations in dynamo behavior under non-spherical geometries. Our numerical simulations further reveal that, the thermal convection weakens in highly distorted stars, and subsequently, the differential rotation is also reduced. These effects may lengthen the conversion timescale between poloidal and toroidal magnetic fields, potentially explaining the newly discovered $P_{\rm cyc}$-$P_{\rm rot}$ relation in cataclysmic variables. △ Less

Submitted 25 February, 2026; originally announced February 2026.

Comments: 7 figures and 1 table in main text; 5 tables and 1 figure in supplement. Accepted by SCPMA

Journal ref: SCIENCE CHINA Physics, Mechanics & Astronomy 69 (2026)

A Bayesian Framework for Human-AI Collaboration: Complementarity and Correlation Neglect

Authors: Saurabh Amin, Amine Bennouna, Daniel Huttenlocher, Dingwen Kong, Liang Lyu, Asuman Ozdaglar

Abstract: We develop a decision-theoretic model of human-AI interaction to study when AI assistance improves or impairs human decision-making. A human decision-maker observes private information and receives a recommendation from an AI system, but may combine these signals imperfectly. We show that the effect of AI assistance decomposes into two main forces: the marginal informational value of the AI beyond… ▽ More We develop a decision-theoretic model of human-AI interaction to study when AI assistance improves or impairs human decision-making. A human decision-maker observes private information and receives a recommendation from an AI system, but may combine these signals imperfectly. We show that the effect of AI assistance decomposes into two main forces: the marginal informational value of the AI beyond what the human already knows, and a behavioral distortion arising from how the human uses the AI's recommendation. Central to our analysis is a micro-founded measure of informational overlap between human and AI knowledge. We study an empirically relevant form of imperfect decision-making -- correlation neglect -- whereby humans treat AI recommendations as independent of their own information despite shared evidence. Under this model, we characterize how overlap and AI capabilities shape the Human-AI interaction regime between augmentation, impairment, complementarity, and automation, and draw key insights. △ Less

Submitted 15 February, 2026; originally announced February 2026.

Compress, Cross and Scale: Multi-Level Compression Cross Networks for Efficient Scaling in Recommender Systems

Authors: Heng Yu, Xiangjun Zhou, Jie Xia, Heng Zhao, Anxin Wu, Yu Zhao, Dongying Kong

Abstract: Modeling high-order feature interactions efficiently is a central challenge in click-through rate and conversion rate prediction. Modern industrial recommender systems are predominantly built upon deep learning recommendation models, where the interaction backbone plays a critical role in determining both predictive performance and system efficiency. However, existing interaction modules often str… ▽ More Modeling high-order feature interactions efficiently is a central challenge in click-through rate and conversion rate prediction. Modern industrial recommender systems are predominantly built upon deep learning recommendation models, where the interaction backbone plays a critical role in determining both predictive performance and system efficiency. However, existing interaction modules often struggle to simultaneously achieve strong interaction capacity, high computational efficiency, and good scalability, resulting in limited ROI when models are scaled under strict production constraints. In this work, we propose MLCC, a structured feature interaction architecture that organizes feature crosses through hierarchical compression and dynamic composition, which can efficiently capture high-order feature dependencies while maintaining favorable computational complexity. We further introduce MC-MLCC, a Multi-Channel extension that decomposes feature interactions into parallel subspaces, enabling efficient horizontal scaling with improved representation capacity and significantly reduced parameter growth. Extensive experiments on three public benchmarks and a large-scale industrial dataset show that our proposed models consistently outperform strong DLRM-style baselines by up to 0.52 AUC, while reducing model parameters and FLOPs by up to 26$\times$ under comparable performance. Comprehensive scaling analyses demonstrate stable and predictable scaling behavior across embedding dimension, head number, and channel count, with channel-based scaling achieving substantially better efficiency than conventional embedding inflation. Finally, online A/B testing on a real-world advertising platform validates the practical effectiveness of our approach, which has been widely adopted in Bilibili advertising system under strict latency and resource constraints. △ Less

Submitted 12 February, 2026; originally announced February 2026.

Comments: 11 pages, 3 figures

Natural Hypergradient Descent: Algorithm Design, Convergence Analysis, and Parallel Implementation

Authors: Deyi Kong, Zaiwei Chen, Shuzhong Zhang, Shancong Mou

Abstract: In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian inverse--we exploit the statistical structure of the inner optimization problem and use the empirical Fisher information matrix as an asymptotically consistent s… ▽ More In this work, we propose Natural Hypergradient Descent (NHGD), a new method for solving bilevel optimization problems. To address the computational bottleneck in hypergradient estimation--namely, the need to compute or approximate Hessian inverse--we exploit the statistical structure of the inner optimization problem and use the empirical Fisher information matrix as an asymptotically consistent surrogate for the Hessian. This design enables a parallel optimize-and-approximate framework in which the Hessian-inverse approximation is updated synchronously with the stochastic inner optimization, reusing gradient information at negligible additional cost. Our main theoretical contribution establishes high-probability error bounds and sample complexity guarantees for NHGD that match those of state-of-the-art optimize-then-approximate methods, while significantly reducing computational time overhead. Empirical evaluations on representative bilevel learning tasks further demonstrate the practical advantages of NHGD, highlighting its scalability and effectiveness in large-scale machine learning settings. △ Less

Submitted 1 April, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

Advancing Block Diffusion Language Models for Test-Time Scaling

Authors: Yi Lu, Deyang Kong, Jianing Wang, Linsen Guo, Xue Wang, Qi Guo, Tao Gui, Xuanjing Huang, Wei Ye, Shikun Zhang, Wei Wang

Abstract: Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, existing BDLMs have limited exploration under the test-time scaling setting and face more severe decoding challenges in long Chain-of-Thought reasoning, particularly in balancing the decoding speed and effectiveness. In this work, we propose a unified fra… ▽ More Recent advances in block diffusion language models have demonstrated competitive performance and strong scalability on reasoning tasks. However, existing BDLMs have limited exploration under the test-time scaling setting and face more severe decoding challenges in long Chain-of-Thought reasoning, particularly in balancing the decoding speed and effectiveness. In this work, we propose a unified framework for test-time scaling in BDLMs that introduces adaptivity in both decoding and block-wise generation. At the decoding level, we propose Bounded Adaptive Confidence Decoding (BACD), a difficulty-aware sampling strategy that dynamically adjusts denoising based on model confidence, accelerating inference while controlling error accumulation. Beyond step-wise adaptivity, we introduce Think Coarse, Critic Fine (TCCF), a test-time scaling paradigm that allocates large block sizes to exploratory reasoning and smaller block sizes to refinement, achieving an effective efficiency-effectiveness balance. To enable efficient and effective decoding with a large block size, we adopt Progressive Block Size Extension, which mitigates performance degradation when scaling block sizes. Extensive experiments show that applying BACD and TCCF to TDAR-8B yields significant improvements over strong baselines such as TraDo-8B (2.26x speedup, +11.2 points on AIME24). These results mark an important step toward unlocking the potential of BDLMs for test-time scaling in complex reasoning tasks. △ Less

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