Showing 1–50 of 679 results for author: Shi, X

SemanticGen: Video Generation in Semantic Space

Authors: Jianhong Bai, Xiaoshi Wu, Xintao Wang, Fu Xiao, Yuanxing Zhang, Qinghe Wang, Xiaoyu Shi, Menghan Xia, Zuozhu Liu, Haoji Hu, Pengfei Wan, Kun Gai

Abstract: State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can generate high-quality videos, it suffers from slow convergence and is computationally expensive when generating long videos. In this paper, we introduce SemanticGen, a novel solution to address these limitations by generatin… ▽ More State-of-the-art video generative models typically learn the distribution of video latents in the VAE space and map them to pixels using a VAE decoder. While this approach can generate high-quality videos, it suffers from slow convergence and is computationally expensive when generating long videos. In this paper, we introduce SemanticGen, a novel solution to address these limitations by generating videos in the semantic space. Our main insight is that, due to the inherent redundancy in videos, the generation process should begin in a compact, high-level semantic space for global planning, followed by the addition of high-frequency details, rather than directly modeling a vast set of low-level video tokens using bi-directional attention. SemanticGen adopts a two-stage generation process. In the first stage, a diffusion model generates compact semantic video features, which define the global layout of the video. In the second stage, another diffusion model generates VAE latents conditioned on these semantic features to produce the final output. We observe that generation in the semantic space leads to faster convergence compared to the VAE latent space. Our method is also effective and computationally efficient when extended to long video generation. Extensive experiments demonstrate that SemanticGen produces high-quality videos and outperforms state-of-the-art approaches and strong baselines. △ Less

Submitted 23 December, 2025; originally announced December 2025.

Comments: Project page: https://jianhongbai.github.io/SemanticGen/

MSC-180: A Benchmark for Automated Formal Theorem Proving from Mathematical Subject Classification

Authors: Sirui Li, Wangyue Lu, Xiaorui Shi, Ke Weng, Haozhe Sun, Minghe Yu, Tiancheng Zhang, Ge Yu, Hengyu Liu, Lun Du

Abstract: Automated Theorem Proving (ATP) represents a core research direction in artificial intelligence for achieving formal reasoning and verification, playing a significant role in advancing machine intelligence. However, current large language model (LLM)-based theorem provers suffer from limitations such as restricted domain coverage and weak generalization in mathematical reasoning. To address these… ▽ More Automated Theorem Proving (ATP) represents a core research direction in artificial intelligence for achieving formal reasoning and verification, playing a significant role in advancing machine intelligence. However, current large language model (LLM)-based theorem provers suffer from limitations such as restricted domain coverage and weak generalization in mathematical reasoning. To address these issues, we propose MSC-180, a benchmark for evaluation based on the MSC2020 mathematical subject classification. It comprises 180 formal verification problems, 3 advanced problems from each of 60 mathematical branches, spanning from undergraduate to graduate levels. Each problem has undergone multiple rounds of verification and refinement by domain experts to ensure formal accuracy. Evaluations of state-of-the-art LLM-based theorem provers under the pass@32 setting reveal that the best model achieves only an 18.89% overall pass rate, with prominent issues including significant domain bias (maximum domain coverage 41.7%) and a difficulty gap (significantly lower pass rates on graduate-level problems). To further quantify performance variability across mathematical domains, we introduce the coefficient of variation (CV) as an evaluation metric. The observed CV values are 4-6 times higher than the statistical high-variability threshold, indicating that the models still rely on pattern matching from training corpora rather than possessing transferable reasoning mechanisms and systematic generalization capabilities. MSC-180, together with its multi-dimensional evaluation framework, provides a discriminative and systematic benchmark for driving the development of next-generation AI systems with genuine mathematical reasoning abilities. △ Less

Submitted 20 December, 2025; originally announced December 2025.

Kling-Omni Technical Report

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

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

Submitted 18 December, 2025; originally announced December 2025.

Comments: Kling-Omni Technical Report

Incentivizing Tool-augmented Thinking with Images for Medical Image Analysis

Authors: Yankai Jiang, Yujie Zhang, Peng Zhang, Yichen Li, Jintai Chen, Xiaoming Shi, Shihui Zhen

Abstract: Recent reasoning based medical MLLMs have made progress in generating step by step textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on fine-grained visual regions to achieve precise grounding and diagnosis. We introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when additional visual e… ▽ More Recent reasoning based medical MLLMs have made progress in generating step by step textual reasoning chains. However, they still struggle with complex tasks that necessitate dynamic and iterative focusing on fine-grained visual regions to achieve precise grounding and diagnosis. We introduce Ophiuchus, a versatile, tool-augmented framework that equips an MLLM to (i) decide when additional visual evidence is needed, (ii) determine where to probe and ground within the medical image, and (iii) seamlessly weave the relevant sub-image content back into an interleaved, multimodal chain of thought. In contrast to prior approaches limited by the performance ceiling of specialized tools, Ophiuchus integrates the model's inherent grounding and perception capabilities with external tools, thereby fostering higher-level reasoning. The core of our method is a three-stage training strategy: cold-start training with tool-integrated reasoning data to achieve basic tool selection and adaptation for inspecting key regions; self-reflection fine-tuning to strengthen reflective reasoning and encourage revisiting tool outputs; and Agentic Tool Reinforcement Learning to directly optimize task-specific rewards and emulate expert-like diagnostic behavior. Extensive experiments show that Ophiuchus consistently outperforms both closed-source and open-source SOTA methods across diverse medical benchmarks, including VQA, detection, and reasoning-based segmentation. Our approach illuminates a path toward medical AI agents that can genuinely "think with images" through tool-integrated reasoning. Datasets, codes, and trained models will be released publicly. △ Less

Submitted 16 December, 2025; originally announced December 2025.

KlingAvatar 2.0 Technical Report

Authors: Kling Team, Jialu Chen, Yikang Ding, Zhixue Fang, Kun Gai, Yuan Gao, Kang He, Jingyun Hua, Boyuan Jiang, Mingming Lao, Xiaohan Li, Hui Liu, Jiwen Liu, Xiaoqiang Liu, Yuan Liu, Shun Lu, Yongsen Mao, Yingchao Shao, Huafeng Shi, Xiaoyu Shi, Peiqin Sun, Songlin Tang, Pengfei Wan, Chao Wang, Xuebo Wang , et al. (3 additional authors not shown)

Abstract: Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos, suffering from temporal drifting, quality degradation, and weak prompt following as video length increases. To address these challenges, we propose KlingAvatar 2.0, a spatio-temporal cascade framework that performs ups… ▽ More Avatar video generation models have achieved remarkable progress in recent years. However, prior work exhibits limited efficiency in generating long-duration high-resolution videos, suffering from temporal drifting, quality degradation, and weak prompt following as video length increases. To address these challenges, we propose KlingAvatar 2.0, a spatio-temporal cascade framework that performs upscaling in both spatial resolution and temporal dimension. The framework first generates low-resolution blueprint video keyframes that capture global semantics and motion, and then refines them into high-resolution, temporally coherent sub-clips using a first-last frame strategy, while retaining smooth temporal transitions in long-form videos. To enhance cross-modal instruction fusion and alignment in extended videos, we introduce a Co-Reasoning Director composed of three modality-specific large language model (LLM) experts. These experts reason about modality priorities and infer underlying user intent, converting inputs into detailed storylines through multi-turn dialogue. A Negative Director further refines negative prompts to improve instruction alignment. Building on these components, we extend the framework to support ID-specific multi-character control. Extensive experiments demonstrate that our model effectively addresses the challenges of efficient, multimodally aligned long-form high-resolution video generation, delivering enhanced visual clarity, realistic lip-teeth rendering with accurate lip synchronization, strong identity preservation, and coherent multimodal instruction following. △ Less

Submitted 15 December, 2025; originally announced December 2025.

Comments: 14 pages, 7 figures

Automated Penetration Testing with LLM Agents and Classical Planning

Authors: Lingzhi Wang, Xinyi Shi, Ziyu Li, Yi Jiang, Shiyu Tan, Yuhao Jiang, Junjie Cheng, Wenyuan Chen, Xiangmin Shen, Zhenyuan LI, Yan Chen

Abstract: While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper, we introduce the "Planner-Executor-Perceptor (PEP)" design paradigm and use it to systematically review existing work and identify the key challenges in this area. We also evaluate existing penetration testing systems, w… ▽ More While penetration testing plays a vital role in cybersecurity, achieving fully automated, hands-off-the-keyboard execution remains a significant research challenge. In this paper, we introduce the "Planner-Executor-Perceptor (PEP)" design paradigm and use it to systematically review existing work and identify the key challenges in this area. We also evaluate existing penetration testing systems, with a particular focus on the use of Large Language Model (LLM) agents for this task. The results show that the out-of-the-box Claude Code and Sonnet 4.5 exhibit superior penetration capabilities observed to date, substantially outperforming all prior systems. However, a detailed analysis of their testing processes reveals specific strengths and limitations; notably, LLM agents struggle with maintaining coherent long-horizon plans, performing complex reasoning, and effectively utilizing specialized tools. These limitations significantly constrain its overall capability, efficiency, and stability. To address these limitations, we propose CHECKMATE, a framework that integrates enhanced classical planning with LLM agents, providing an external, structured "brain" that mitigates the inherent weaknesses of LLM agents. Our evaluation shows that CHECKMATE outperforms the state-of-the-art system (Claude Code) in penetration capability, improving benchmark success rates by over 20%. In addition, it delivers substantially greater stability, cutting both time and monetary costs by more than 50%. △ Less

Submitted 11 December, 2025; originally announced December 2025.

PCMind-2.1-Kaiyuan-2B Technical Report

Authors: Kairong Luo, Zhenbo Sun, Xinyu Shi, Shengqi Chen, Bowen Yu, Yunyi Chen, Chenyi Dang, Hengtao Tao, Hui Wang, Fangming Liu, Kaifeng Lyu, Wenguang Chen

Abstract: The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relies on closed-source, high-quality data and training recipes. To address this, we introduce PCMind-2.1-Kaiyuan-2B, a fully open-source 2-billion-parameter model focused on improving training efficiency and effectiveness un… ▽ More The rapid advancement of Large Language Models (LLMs) has resulted in a significant knowledge gap between the open-source community and industry, primarily because the latter relies on closed-source, high-quality data and training recipes. To address this, we introduce PCMind-2.1-Kaiyuan-2B, a fully open-source 2-billion-parameter model focused on improving training efficiency and effectiveness under resource constraints. Our methodology includes three key innovations: a Quantile Data Benchmarking method for systematically comparing heterogeneous open-source datasets and providing insights on data mixing strategies; a Strategic Selective Repetition scheme within a multi-phase paradigm to effectively leverage sparse, high-quality data; and a Multi-Domain Curriculum Training policy that orders samples by quality. Supported by a highly optimized data preprocessing pipeline and architectural modifications for FP16 stability, Kaiyuan-2B achieves performance competitive with state-of-the-art fully open-source models, demonstrating practical and scalable solutions for resource-limited pretraining. We release all assets (including model weights, data, and code) under Apache 2.0 license at https://huggingface.co/thu-pacman/PCMind-2.1-Kaiyuan-2B. △ Less

Submitted 8 December, 2025; originally announced December 2025.

Fast SceneScript: Accurate and Efficient Structured Language Model via Multi-Token Prediction

Authors: Ruihong Yin, Xuepeng Shi, Oleksandr Bailo, Marco Manfredi, Theo Gevers

Abstract: Recent perception-generalist approaches based on language models have achieved state-of-the-art results across diverse tasks, including 3D scene layout estimation, via unified architecture and interface. However, these approaches rely on autoregressive next-token prediction, which is inherently slow. In this work, we introduce Fast SceneScript, a novel structured language model for accurate and ef… ▽ More Recent perception-generalist approaches based on language models have achieved state-of-the-art results across diverse tasks, including 3D scene layout estimation, via unified architecture and interface. However, these approaches rely on autoregressive next-token prediction, which is inherently slow. In this work, we introduce Fast SceneScript, a novel structured language model for accurate and efficient 3D scene layout estimation. Our method employs multi-token prediction (MTP) to reduce the number of autoregressive iterations and significantly accelerate inference. While MTP improves speed, unreliable token predictions can significantly reduce accuracy. To filter out unreliable tokens, we adapt self-speculative decoding (SSD) for structured language models and introduce confidence-guided decoding (CGD) with an improved scoring mechanism for token reliability. Furthermore, we design a parameter-efficient mechanism that reduces the parameter overhead of MTP. Extensive experiments on the ASE and Structured3D benchmarks demonstrate that Fast SceneScript can generate up to 9 tokens per decoder inference step without compromising accuracy, while adding only $\sim7.5\%$ additional parameters. △ Less

Submitted 5 December, 2025; originally announced December 2025.

Comments: 10 pages, 8 figures

DINO-RotateMatch: A Rotation-Aware Deep Framework for Robust Image Matching in Large-Scale 3D Reconstruction

Authors: Kaichen Zhang, Tianxiang Sheng, Xuanming Shi

Abstract: This paper presents DINO-RotateMatch, a deep-learning framework designed to address the chal lenges of image matching in large-scale 3D reconstruction from unstructured Internet images. The method integrates a dataset-adaptive image pairing strategy with rotation-aware keypoint extraction and matching. DINO is employed to retrieve semantically relevant image pairs in large collections, while… ▽ More This paper presents DINO-RotateMatch, a deep-learning framework designed to address the chal lenges of image matching in large-scale 3D reconstruction from unstructured Internet images. The method integrates a dataset-adaptive image pairing strategy with rotation-aware keypoint extraction and matching. DINO is employed to retrieve semantically relevant image pairs in large collections, while rotation-based augmentation captures orientation-dependent local features using ALIKED and Light Glue. Experiments on the Kaggle Image Matching Challenge 2025 demonstrate consistent improve ments in mean Average Accuracy (mAA), achieving a Silver Award (47th of 943 teams). The results confirm that combining self-supervised global descriptors with rotation-enhanced local matching offers a robust and scalable solution for large-scale 3D reconstruction. △ Less

Submitted 3 December, 2025; originally announced December 2025.

Comments: 9 pages, 5 figures, 1 table

MultiShotMaster: A Controllable Multi-Shot Video Generation Framework

Authors: Qinghe Wang, Xiaoyu Shi, Baolu Li, Weikang Bian, Quande Liu, Huchuan Lu, Xintao Wang, Pengfei Wan, Kun Gai, Xu Jia

Abstract: Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and controllability beyond text prompts. To tackle these challenges, we propose MultiShotMaster, a framework for highly controllable multi-shot video generation. We extend a pretrained single-shot model by integrating two n… ▽ More Current video generation techniques excel at single-shot clips but struggle to produce narrative multi-shot videos, which require flexible shot arrangement, coherent narrative, and controllability beyond text prompts. To tackle these challenges, we propose MultiShotMaster, a framework for highly controllable multi-shot video generation. We extend a pretrained single-shot model by integrating two novel variants of RoPE. First, we introduce Multi-Shot Narrative RoPE, which applies explicit phase shift at shot transitions, enabling flexible shot arrangement while preserving the temporal narrative order. Second, we design Spatiotemporal Position-Aware RoPE to incorporate reference tokens and grounding signals, enabling spatiotemporal-grounded reference injection. In addition, to overcome data scarcity, we establish an automated data annotation pipeline to extract multi-shot videos, captions, cross-shot grounding signals and reference images. Our framework leverages the intrinsic architectural properties to support multi-shot video generation, featuring text-driven inter-shot consistency, customized subject with motion control, and background-driven customized scene. Both shot count and duration are flexibly configurable. Extensive experiments demonstrate the superior performance and outstanding controllability of our framework. △ Less

Submitted 2 December, 2025; originally announced December 2025.

Comments: Project Page: https://qinghew.github.io/MultiShotMaster

OmniPerson: Unified Identity-Preserving Pedestrian Generation

Authors: Changxiao Ma, Chao Yuan, Xincheng Shi, Yuzhuo Ma, Yongfei Zhang, Longkun Zhou, Yujia Zhang, Shangze Li, Yifan Xu

Abstract: Person re-identification (ReID) suffers from a lack of large-scale high-quality training data due to challenges in data privacy and annotation costs. While previous approaches have explored pedestrian generation for data augmentation, they often fail to ensure identity consistency and suffer from insufficient controllability, thereby limiting their effectiveness in dataset augmentation. To address… ▽ More Person re-identification (ReID) suffers from a lack of large-scale high-quality training data due to challenges in data privacy and annotation costs. While previous approaches have explored pedestrian generation for data augmentation, they often fail to ensure identity consistency and suffer from insufficient controllability, thereby limiting their effectiveness in dataset augmentation. To address this, We introduce OmniPerson, the first unified identity-preserving pedestrian generation pipeline for visible/infrared image/video ReID tasks. Our contributions are threefold: 1) We proposed OmniPerson, a unified generation model, offering holistic and fine-grained control over all key pedestrian attributes. Supporting RGB/IR modality image/video generation with any number of reference images, two kinds of person poses, and text. Also including RGB-to-IR transfer and image super-resolution abilities.2) We designed Multi-Refer Fuser for robust identity preservation with any number of reference images as input, making OmniPerson could distill a unified identity from a set of multi-view reference images, ensuring our generated pedestrians achieve high-fidelity pedestrian generation.3) We introduce PersonSyn, the first large-scale dataset for multi-reference, controllable pedestrian generation, and present its automated curation pipeline which transforms public, ID-only ReID benchmarks into a richly annotated resource with the dense, multi-modal supervision required for this task. Experimental results demonstrate that OmniPerson achieves SoTA in pedestrian generation, excelling in both visual fidelity and identity consistency. Furthermore, augmenting existing datasets with our generated data consistently improves the performance of ReID models. We will open-source the full codebase, pretrained model, and the PersonSyn dataset. △ Less

Submitted 2 December, 2025; originally announced December 2025.

LEC: Linear Expectation Constraints for False-Discovery Control in Selective Prediction and Routing Systems

Authors: Zhiyuan Wang, Aniri, Tianlong Chen, Yue Zhang, Heng Tao Shen, Xiaoshuang Shi, Kaidi Xu

Abstract: Large language models (LLMs) often generate unreliable answers, while heuristic uncertainty methods fail to fully distinguish correct from incorrect predictions, causing users to accept erroneous answers without statistical guarantees. We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed… ▽ More Large language models (LLMs) often generate unreliable answers, while heuristic uncertainty methods fail to fully distinguish correct from incorrect predictions, causing users to accept erroneous answers without statistical guarantees. We address this issue through the lens of false discovery rate (FDR) control, ensuring that among all accepted predictions, the proportion of errors does not exceed a target risk level. To achieve this in a principled way, we propose LEC, which reinterprets selective prediction as a constrained decision problem by enforcing a Linear Expectation Constraint over selection and error indicators. Then, we establish a finite-sample sufficient condition, which relies only on a held-out set of exchangeable calibration samples, to compute an FDR-constrained, coverage-maximizing threshold. Furthermore, we extend LEC to a two-model routing mechanism: given a prompt, if the current model's uncertainty exceeds its calibrated threshold, we delegate it to a stronger model, while maintaining a unified FDR guarantee. Evaluations on closed-ended and open-ended question-answering (QA) datasets show that LEC achieves tighter FDR control and substantially improves sample retention over prior methods. Moreover, the two-model routing mechanism achieves lower risk levels while accepting more correct samples than each individual model. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Leveraging Channel Knowledge Map for Multi-User Hierarchical Beam Training Under Position Uncertainty

Authors: Xu Shi, Haohan Wang, Yashuai Cao, Hengyu Zhang, Sufang Yang, Jintao Wang

Abstract: Channel knowledge map (CKM) emerges as a promising framework to acquire location-specific channel information without consuming wireless resources, creating new horizons for advanced wireless network design and optimization. Despite its potential, the practical application of CKM in beam training faces several challenges. On one hand, the user's precise location is typically unavailable prior to b… ▽ More Channel knowledge map (CKM) emerges as a promising framework to acquire location-specific channel information without consuming wireless resources, creating new horizons for advanced wireless network design and optimization. Despite its potential, the practical application of CKM in beam training faces several challenges. On one hand, the user's precise location is typically unavailable prior to beam training, which limits the utility of CKM since its effectiveness relies heavily on accurate input of position data. On the other hand, the intricate interplay among CKM, real-time observations, and training strategies has not been thoroughly studied, leading to suboptimal performance and difficulties in practical implementation. In this paper, we present a framework for CKM-aided beam training that addresses these limitations. For single-user scenario, we propose a reward-motivated beam-potential hierarchical strategy which integrates partial position information and CKM. This strategy models the user equipment (UE) position uncertainty and formulates the hierarchical searching process as a pruned binary search tree. An optimal hierarchical searching strategy with minimal overhead is derived by evaluating the weights and rewards of potential codewords. Furthermore, a low-complexity two-layer lookahead scheme is designed to balance overhead and computational demands. For multi-user scenario, we develop a correlation-driven position-pruning training scheme, where sidelobe gains from inter-user interference are exploited to provide additional side information for overhead reduction, allowing all users to be simultaneously assigned their respective supportive beams. Simulations validate the superior performances of proposed approaches in advancing 6G beam training. △ Less

Submitted 28 November, 2025; originally announced November 2025.

RecToM: A Benchmark for Evaluating Machine Theory of Mind in LLM-based Conversational Recommender Systems

Authors: Mengfan Li, Xuanhua Shi, Yang Deng

Abstract: Large Language models are revolutionizing the conversational recommender systems through their impressive capabilities in instruction comprehension, reasoning, and human interaction. A core factor underlying effective recommendation dialogue is the ability to infer and reason about users' mental states (such as desire, intention, and belief), a cognitive capacity commonly referred to as Theory of… ▽ More Large Language models are revolutionizing the conversational recommender systems through their impressive capabilities in instruction comprehension, reasoning, and human interaction. A core factor underlying effective recommendation dialogue is the ability to infer and reason about users' mental states (such as desire, intention, and belief), a cognitive capacity commonly referred to as Theory of Mind. Despite growing interest in evaluating ToM in LLMs, current benchmarks predominantly rely on synthetic narratives inspired by Sally-Anne test, which emphasize physical perception and fail to capture the complexity of mental state inference in realistic conversational settings. Moreover, existing benchmarks often overlook a critical component of human ToM: behavioral prediction, the ability to use inferred mental states to guide strategic decision-making and select appropriate conversational actions for future interactions. To better align LLM-based ToM evaluation with human-like social reasoning, we propose RecToM, a novel benchmark for evaluating ToM abilities in recommendation dialogues. RecToM focuses on two complementary dimensions: Cognitive Inference and Behavioral Prediction. The former focus on understanding what has been communicated by inferring the underlying mental states. The latter emphasizes what should be done next, evaluating whether LLMs can leverage these inferred mental states to predict, select, and assess appropriate dialogue strategies. Extensive experiments on state-of-the-art LLMs demonstrate that RecToM poses a significant challenge. While the models exhibit partial competence in recognizing mental states, they struggle to maintain coherent, strategic ToM reasoning throughout dynamic recommendation dialogues, particularly in tracking evolving intentions and aligning conversational strategies with inferred mental states. △ Less

Submitted 27 November, 2025; originally announced November 2025.

Comments: Accepted by AAAI 2026

EM2LDL: A Multilingual Speech Corpus for Mixed Emotion Recognition through Label Distribution Learning

Authors: Xingfeng Li, Xiaohan Shi, Junjie Li, Yongwei Li, Masashi Unoki, Tomoki Toda, Masato Akagi

Abstract: This study introduces EM2LDL, a novel multilingual speech corpus designed to advance mixed emotion recognition through label distribution learning. Addressing the limitations of predominantly monolingual and single-label emotion corpora \textcolor{black}{that restrict linguistic diversity, are unable to model mixed emotions, and lack ecological validity}, EM2LDL comprises expressive utterances in… ▽ More This study introduces EM2LDL, a novel multilingual speech corpus designed to advance mixed emotion recognition through label distribution learning. Addressing the limitations of predominantly monolingual and single-label emotion corpora \textcolor{black}{that restrict linguistic diversity, are unable to model mixed emotions, and lack ecological validity}, EM2LDL comprises expressive utterances in English, Mandarin, and Cantonese, capturing the intra-utterance code-switching prevalent in multilingual regions like Hong Kong and Macao. The corpus integrates spontaneous emotional expressions from online platforms, annotated with fine-grained emotion distributions across 32 categories. Experimental baselines using self-supervised learning models demonstrate robust performance in speaker-independent gender-, age-, and personality-based evaluations, with HuBERT-large-EN achieving optimal results. By incorporating linguistic diversity and ecological validity, EM2LDL enables the exploration of complex emotional dynamics in multilingual settings. This work provides a versatile testbed for developing adaptive, empathetic systems for applications in affective computing, including mental health monitoring and cross-cultural communication. The dataset, annotations, and baseline codes are publicly available at https://github.com/xingfengli/EM2LDL. △ Less

Submitted 25 November, 2025; originally announced November 2025.

Comments: Submitted to IEEE Transactions on Affective computing

RED-F: Reconstruction-Elimination based Dual-stream Contrastive Forecasting for Multivariate Time Series Anomaly Prediction

Authors: PengYu Chen, Xiaohou Shi, Yuan Chang, Yan Sun, Sajal K. Das

Abstract: The proactive prediction of anomalies (AP) in multivariate time series (MTS) is a critical challenge to ensure system dependability. The difficulty lies in identifying subtle anomaly precursors concealed within normal signals. However, existing unsupervised methods, trained exclusively on normal data, demonstrate a fundamental propensity to reconstruct normal patterns. Consequently, when confronte… ▽ More The proactive prediction of anomalies (AP) in multivariate time series (MTS) is a critical challenge to ensure system dependability. The difficulty lies in identifying subtle anomaly precursors concealed within normal signals. However, existing unsupervised methods, trained exclusively on normal data, demonstrate a fundamental propensity to reconstruct normal patterns. Consequently, when confronted with weak precursors, their predictions are dominated by the normal pattern, submerging the very signal required for prediction. To contend with the limitation, we propose RED-F, a Reconstruction-Elimination based Dual-stream Contrastive Forecasting framework, comprising the Reconstruction-Elimination Model (REM) and the Dual-stream Contrastive Forecasting Model (DFM). The REM utilizes a hybrid time-frequency mechanism to mitigate the precursor, generating a purified, normal-pattern baseline. The DFM then receives this purified baseline and the original sequence which retains the precursor as parallel inputs. At the core of our framework, RED-F employs a contrastive forecast that transforms the difficult task of absolute signal detection into a simpler, more robust task of relative trajectory comparison by computing the divergence between these two predictive streams. This contrastive mechanism serves to amplify the faint precursor signal. Furthermore, the DFM is trained with a novel Multi-Series Prediction (MSP) objective, which leverages distant future context to enhance its predictive sensitivity. Extensive experiments on six real-world datasets demonstrate the superior capability of RED-F in anomaly prediction tasks. △ Less

Submitted 25 November, 2025; originally announced November 2025.

Comments: 13 pages, 12 figures

How Learning Rate Decay Wastes Your Best Data in Curriculum-Based LLM Pretraining

Authors: Kairong Luo, Zhenbo Sun, Haodong Wen, Xinyu Shi, Jiarui Cui, Chenyi Dang, Kaifeng Lyu, Wenguang Chen

Abstract: Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A natural approach to better leverage high-quality data is curriculum-based pretraining, where the model is trained on data sorted in ascending order of quality as determined by a quality metric. However, prior studies hav… ▽ More Due to the scarcity of high-quality data, large language models (LLMs) are often trained on mixtures of data with varying quality levels, even after sophisticated data curation. A natural approach to better leverage high-quality data is curriculum-based pretraining, where the model is trained on data sorted in ascending order of quality as determined by a quality metric. However, prior studies have reported limited improvements from such curriculum-based pretraining strategies. This work identifies a critical factor constraining these methods: the incompatibility between the ascending data quality order and the decaying learning rate (LR) schedule. We find that while curriculum-based training substantially outperforms random shuffling when using a constant LR, its advantage diminishes under standard LR decay schedules. Our experiments show this incompatibility can be mitigated by two simple strategies: (1) employing a more moderate LR decay schedule, where the final LR is only moderately smaller than the peak LR, and (2) replacing LR decay with model averaging, i.e., computing a weighted average of the final few checkpoints. By combining these strategies, we improve the average score on a suite of standard benchmarks by 1.64% over random shuffling, without additional data refinement. Validated on 1.5B-parameter models trained over 30B tokens with various data-quality metrics, our findings call for a re-evaluation of curriculum-based LLM pretraining and underscore the potential of co-designing data curricula with optimization methods. △ Less

Submitted 24 November, 2025; originally announced November 2025.

ConsistCompose: Unified Multimodal Layout Control for Image Composition

Authors: Xuanke Shi, Boxuan Li, Xiaoyang Han, Zhongang Cai, Lei Yang, Dahua Lin, Quan Wang

Abstract: Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with image regions-while their generative counterpart, linguistic-embedded layout-grounded generation (LELG) for layout-controllable multi-instance generation, remains underexplored and limits precise compositional control. We pr… ▽ More Unified multimodal models that couple visual understanding with image generation have advanced rapidly, yet most systems still focus on visual grounding-aligning language with image regions-while their generative counterpart, linguistic-embedded layout-grounded generation (LELG) for layout-controllable multi-instance generation, remains underexplored and limits precise compositional control. We present ConsistCompose, a unified multimodal framework that embeds layout coordinates directly into language prompts, enabling layout-controlled multi-instance image generation from Interleaved Image-Text within a single generative interface. We further construct ConsistCompose3M, a 3.4M multi-instance generation dataset with layout and identity annotations (2.6M text-guided and 0.8M image-guided data pairs) that provides large-scale supervision for layout-conditioned generation. Within this framework, LELG is instantiated through instance-coordinate binding prompts and coordinate-aware classifier-free guidance, which translate linguistic layout cues into precise spatial control without task-specific branches. Experiments on COCO-Position and MS-Bench show that ConsistCompose substantially improves spatial accuracy over layout-controlled baselines while preserving identity fidelity and competitive general multimodal understanding, establishing a unified paradigm for layout-controllable multimodal image generation. △ Less

Submitted 11 December, 2025; v1 submitted 23 November, 2025; originally announced November 2025.

Comments: 22 pages, 17 figures

Gate-level boolean evolutionary geometric attention neural networks

Authors: Xianshuai Shi, Jianfeng Zhu, Leibo Liu

Abstract: This paper presents a gate-level Boolean evolutionary geometric attention neural network that models images as Boolean fields governed by logic gates. Each pixel is a Boolean variable (0 or 1) embedded on a two-dimensional geometric manifold (for example, a discrete toroidal lattice), which defines adjacency and information propagation among pixels. The network updates image states through a Boole… ▽ More This paper presents a gate-level Boolean evolutionary geometric attention neural network that models images as Boolean fields governed by logic gates. Each pixel is a Boolean variable (0 or 1) embedded on a two-dimensional geometric manifold (for example, a discrete toroidal lattice), which defines adjacency and information propagation among pixels. The network updates image states through a Boolean reaction-diffusion mechanism: pixels receive Boolean diffusion from neighboring pixels (diffusion process) and perform local logic updates via trainable gate-level logic kernels (reaction process), forming a reaction-diffusion logic network. A Boolean self-attention mechanism is introduced, using XNOR-based Boolean Query-Key (Q-K) attention to modulate neighborhood diffusion pathways and realize logic attention. We also propose Boolean Rotary Position Embedding (RoPE), which encodes relative distances by parity-bit flipping to simulate Boolean ``phase'' offsets. The overall structure resembles a Transformer but operates entirely in the Boolean domain. Trainable parameters include Q-K pattern bits and gate-level kernel configurations. Because outputs are discrete, continuous relaxation methods (such as sigmoid approximation or soft-logic operators) ensure differentiable training. Theoretical analysis shows that the network achieves universal expressivity, interpretability, and hardware efficiency, capable of reproducing convolutional and attention mechanisms. Applications include high-speed image processing, interpretable artificial intelligence, and digital hardware acceleration, offering promising future research directions. △ Less

Submitted 11 November, 2025; originally announced November 2025.

InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policy

Authors: Yang Tian, Yuyin Yang, Yiman Xie, Zetao Cai, Xu Shi, Ning Gao, Hangxu Liu, Xuekun Jiang, Zherui Qiu, Feng Yuan, Yaping Li, Ping Wang, Junhao Cai, Jia Zeng, Hao Dong, Jiangmiao Pang

Abstract: Recent works explore how real and synthetic data contribute to Vision-Language-Action (VLA) models' generalization. While current VLA models have shown the strong effectiveness of large-scale real-robot pre-training, synthetic data has not previously demonstrated comparable capability at scale. This paper provides the first evidence that synthetic data alone can match the performance of the strong… ▽ More Recent works explore how real and synthetic data contribute to Vision-Language-Action (VLA) models' generalization. While current VLA models have shown the strong effectiveness of large-scale real-robot pre-training, synthetic data has not previously demonstrated comparable capability at scale. This paper provides the first evidence that synthetic data alone can match the performance of the strongest $π$-dataset in pre-training a VLA model, revealing the substantial value of large-scale simulation. The resulting model also exhibits surprisingly zero-shot sim-to-real transfer on several challenging tasks. Our synthetic dataset, InternData-A1, contains over 630k trajectories and 7,433 hours across 4 embodiments, 18 skills, 70 tasks, and 227 scenes, covering rigid, articulated, deformable, and fluid-object manipulation. It is generated through a highly autonomous, fully decoupled, and compositional simulation pipeline that enables long-horizon skill composition, flexible task assembly, and heterogeneous embodiments with minimal manual tuning. Using the same architecture as $π_0$, we pre-train a model entirely on InternData-A1 and find that it matches the official $π_0$ across 49 simulation tasks, 5 real-world tasks, and 4 long-horizon dexterous tasks. We release the dataset and will open-source the generation pipeline to broaden access to large-scale robotic data and to lower the barrier to scalable data creation for embodied AI research. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Revisiting Fairness-aware Interactive Recommendation: Item Lifecycle as a Control Knob

Authors: Yun Lu, Xiaoyu Shi, Hong Xie, Chongjun Xia, Zhenhui Gong, Mingsheng Shang

Abstract: This paper revisits fairness-aware interactive recommendation (e.g., TikTok, KuaiShou) by introducing a novel control knob, i.e., the lifecycle of items. We make threefold contributions. First, we conduct a comprehensive empirical analysis and uncover that item lifecycles in short-video platforms follow a compressed three-phase pattern, i.e., rapid growth, transient stability, and sharp decay, whi… ▽ More This paper revisits fairness-aware interactive recommendation (e.g., TikTok, KuaiShou) by introducing a novel control knob, i.e., the lifecycle of items. We make threefold contributions. First, we conduct a comprehensive empirical analysis and uncover that item lifecycles in short-video platforms follow a compressed three-phase pattern, i.e., rapid growth, transient stability, and sharp decay, which significantly deviates from the classical four-stage model (introduction, growth, maturity, decline). Second, we introduce LHRL, a lifecycle-aware hierarchical reinforcement learning framework that dynamically harmonizes fairness and accuracy by leveraging phase-specific exposure dynamics. LHRL consists of two key components: (1) PhaseFormer, a lightweight encoder combining STL decomposition and attention mechanisms for robust phase detection; (2) a two-level HRL agent, where the high-level policy imposes phase-aware fairness constraints, and the low-level policy optimizes immediate user engagement. This decoupled optimization allows for effective reconciliation between long-term equity and short-term utility. Third, experiments on multiple real-world interactive recommendation datasets demonstrate that LHRL significantly improves both fairness and user engagement. Furthermore, the integration of lifecycle-aware rewards into existing RL-based models consistently yields performance gains, highlighting the generalizability and practical value of our approach. △ Less

Submitted 20 November, 2025; originally announced November 2025.

Comments: 8 pages, 5 figures, conference

EVA-Net: Interpretable Anomaly Detection for Brain Health via Learning Continuous Aging Prototypes from One-Class EEG Cohorts

Authors: Kunyu Zhang, Mingxuan Wang, Xiangjie Shi, Haoxing Xu, Chao Zhang

Abstract: The brain age is a key indicator of brain health. While electroencephalography (EEG) is a practical tool for this task, existing models struggle with the common challenge of imperfect medical data, such as learning a ``normal'' baseline from weakly supervised, healthy-only cohorts. This is a critical anomaly detection task for identifying disease, but standard models are often black boxes lacking… ▽ More The brain age is a key indicator of brain health. While electroencephalography (EEG) is a practical tool for this task, existing models struggle with the common challenge of imperfect medical data, such as learning a ``normal'' baseline from weakly supervised, healthy-only cohorts. This is a critical anomaly detection task for identifying disease, but standard models are often black boxes lacking an interpretable structure. We propose EVA-Net, a novel framework that recasts brain age as an interpretable anomaly detection problem. EVA-Net uses an efficient, sparsified-attention Transformer to model long EEG sequences. To handle noise and variability in imperfect data, it employs a Variational Information Bottleneck to learn a robust, compressed representation. For interpretability, this representation is aligned to a continuous prototype network that explicitly learns the normative healthy aging manifold. Trained on 1297 healthy subjects, EVA-Net achieves state-of-the-art accuracy. We validated its anomaly detection capabilities on an unseen cohort of 27 MCI and AD patients. This pathological group showed significantly higher brain-age gaps and a novel Prototype Alignment Error, confirming their deviation from the healthy manifold. EVA-Net provides an interpretable framework for healthcare intelligence using imperfect medical data. △ Less

Submitted 23 November, 2025; v1 submitted 19 November, 2025; originally announced November 2025.

$π^{*}_{0.6}$: a VLA That Learns From Experience

Authors: Physical Intelligence, Ali Amin, Raichelle Aniceto, Ashwin Balakrishna, Kevin Black, Ken Conley, Grace Connors, James Darpinian, Karan Dhabalia, Jared DiCarlo, Danny Driess, Michael Equi, Adnan Esmail, Yunhao Fang, Chelsea Finn, Catherine Glossop, Thomas Godden, Ivan Goryachev, Lachy Groom, Hunter Hancock, Karol Hausman, Gashon Hussein, Brian Ichter, Szymon Jakubczak, Rowan Jen , et al. (31 additional authors not shown)

Abstract: We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demon… ▽ More We study how vision-language-action (VLA) models can improve through real-world deployments via reinforcement learning (RL). We present a general-purpose method, RL with Experience and Corrections via Advantage-conditioned Policies (RECAP), that provides for RL training of VLAs via advantage conditioning. Our method incorporates heterogeneous data into the self-improvement process, including demonstrations, data from on-policy collection, and expert teleoperated interventions provided during autonomous execution. RECAP starts by pre-training a generalist VLA with offline RL, which we call $π^{*}_{0.6}$, that can then be specialized to attain high performance on downstream tasks through on-robot data collection. We show that the $π^{*}_{0.6}$ model trained with the full RECAP method can fold laundry in real homes, reliably assemble boxes, and make espresso drinks using a professional espresso machine. On some of the hardest tasks, RECAP more than doubles task throughput and roughly halves the task failure rate. △ Less

Submitted 18 November, 2025; v1 submitted 18 November, 2025; originally announced November 2025.

Scaling Spatial Intelligence with Multimodal Foundation Models

Authors: Zhongang Cai, Ruisi Wang, Chenyang Gu, Fanyi Pu, Junxiang Xu, Yubo Wang, Wanqi Yin, Zhitao Yang, Chen Wei, Qingping Sun, Tongxi Zhou, Jiaqi Li, Hui En Pang, Oscar Qian, Yukun Wei, Zhiqian Lin, Xuanke Shi, Kewang Deng, Xiaoyang Han, Zukai Chen, Xiangyu Fan, Hanming Deng, Lewei Lu, Liang Pan, Bo Li , et al. (4 additional authors not shown)

Abstract: Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and gen… ▽ More Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel). We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M: eight million diverse data samples under a rigorous taxonomy of spatial capabilities. SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks: 68.7% on VSI-Bench, 43.3% on MMSI, 85.6% on MindCube, 54.6% on ViewSpatial, and 50.1% on SITE, while maintaining strong general multimodal understanding (e.g., 84.9% on MMBench-En). More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training, analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. SenseNova-SI is an ongoing project, and this report will be updated continuously. All newly trained multimodal foundation models are publicly released to facilitate further research in this direction. △ Less

Submitted 27 November, 2025; v1 submitted 17 November, 2025; originally announced November 2025.

Comments: Codebase: https://github.com/OpenSenseNova/SenseNova-SI; Models: https://huggingface.co/collections/sensenova/sensenova-si

LIHE: Linguistic Instance-Split Hyperbolic-Euclidean Framework for Generalized Weakly-Supervised Referring Expression Comprehension

Authors: Xianglong Shi, Silin Cheng, Sirui Zhao, Yunhan Jiang, Enhong Chen, Yang Liu, Sebastien Ourselin

Abstract: Existing Weakly-Supervised Referring Expression Comprehension (WREC) methods, while effective, are fundamentally limited by a one-to-one mapping assumption, hindering their ability to handle expressions corresponding to zero or multiple targets in realistic scenarios. To bridge this gap, we introduce the Weakly-Supervised Generalized Referring Expression Comprehension task (WGREC), a more practica… ▽ More Existing Weakly-Supervised Referring Expression Comprehension (WREC) methods, while effective, are fundamentally limited by a one-to-one mapping assumption, hindering their ability to handle expressions corresponding to zero or multiple targets in realistic scenarios. To bridge this gap, we introduce the Weakly-Supervised Generalized Referring Expression Comprehension task (WGREC), a more practical paradigm that handles expressions with variable numbers of referents. However, extending WREC to WGREC presents two fundamental challenges: supervisory signal ambiguity, where weak image-level supervision is insufficient for training a model to infer the correct number and identity of referents, and semantic representation collapse, where standard Euclidean similarity forces hierarchically-related concepts into non-discriminative clusters, blurring categorical boundaries. To tackle these challenges, we propose a novel WGREC framework named Linguistic Instance-Split Hyperbolic-Euclidean (LIHE), which operates in two stages. The first stage, Referential Decoupling, predicts the number of target objects and decomposes the complex expression into simpler sub-expressions. The second stage, Referent Grounding, then localizes these sub-expressions using HEMix, our innovative hybrid similarity module that synergistically combines the precise alignment capabilities of Euclidean proximity with the hierarchical modeling strengths of hyperbolic geometry. This hybrid approach effectively prevents semantic collapse while preserving fine-grained distinctions between related concepts. Extensive experiments demonstrate LIHE establishes the first effective weakly supervised WGREC baseline on gRefCOCO and Ref-ZOM, while HEMix achieves consistent improvements on standard REC benchmarks, improving IoU@0.5 by up to 2.5\%. The code is available at https://anonymous.4open.science/r/LIHE. △ Less

Submitted 14 November, 2025; originally announced November 2025.

HeteroSTA: A CPU-GPU Heterogeneous Static Timing Analysis Engine with Holistic Industrial Design Support

Authors: Zizheng Guo, Haichuan Liu, Xizhe Shi, Shenglu Hua, Zuodong Zhang, Chunyuan Zhao, Runsheng Wang, Yibo Lin

Abstract: We introduce in this paper, HeteroSTA, the first CPU-GPU heterogeneous timing analysis engine that efficiently supports: (1) a set of delay calculation models providing versatile accuracy-speed choices without relying on an external golden tool, (2) robust support for industry formats, including especially the .sdc constraints containing all common timing exceptions, clock domains, and case analys… ▽ More We introduce in this paper, HeteroSTA, the first CPU-GPU heterogeneous timing analysis engine that efficiently supports: (1) a set of delay calculation models providing versatile accuracy-speed choices without relying on an external golden tool, (2) robust support for industry formats, including especially the .sdc constraints containing all common timing exceptions, clock domains, and case analysis modes, and (3) end-to-end GPU-acceleration for both graph-based and path-based timing queries, all exposed as a zero-overhead flattened heterogeneous application programming interface (API). HeteroSTA is publicly available with both a standalone binary executable and an embeddable shared library targeting ubiquitous academic and industry applications. Example use cases as a standalone tool, a timing-driven DREAMPlace 4.0 integration, and a timing-driven global routing integration have all demonstrated remarkable runtime speed-up and comparable quality. △ Less

Submitted 11 November, 2025; originally announced November 2025.

Comments: 7 pages, 3 figures, to be published in ASP-DAC 2026

GraphFaaS: Serverless GNN Inference for Burst-Resilient, Real-Time Intrusion Detection

Authors: Lingzhi Wang, Vinod Yegneswaran, Xinyi Shi, Ziyu Li, Ashish Gehani, Yan Chen

Abstract: Provenance-based intrusion detection is an increasingly popular application of graphical machine learning in cybersecurity, where system activities are modeled as provenance graphs to capture causality and correlations among potentially malicious actions. Graph Neural Networks (GNNs) have demonstrated strong performance in this setting. However, traditional statically-provisioned GNN inference arc… ▽ More Provenance-based intrusion detection is an increasingly popular application of graphical machine learning in cybersecurity, where system activities are modeled as provenance graphs to capture causality and correlations among potentially malicious actions. Graph Neural Networks (GNNs) have demonstrated strong performance in this setting. However, traditional statically-provisioned GNN inference architectures fall short in meeting two crucial demands of intrusion detection: (1) maintaining consistently low detection latency, and (2) handling highly irregular and bursty workloads. To holistically address these challenges, we present GraphFaaS, a serverless architecture tailored for GNN-based intrusion detection. GraphFaaS leverages the elasticity and agility of serverless computing to dynamically scale the GNN inference pipeline. We parallelize and adapt GNN workflows to a serverless environment, ensuring that the system can respond in real time to fluctuating workloads. By decoupling compute resources from static provisioning, GraphFaaS delivers stable inference latency, which is critical for dependable intrusion detection and timely incident response in cybersecurity operations. Preliminary evaluation shows GraphFaaS reduces average detection latency by 85% and coefficient of variation (CV) by 64% compared to the baseline. △ Less

Submitted 13 November, 2025; originally announced November 2025.

Comments: Accepted by ML For Systems workshop at Neural Information Processing Systems (NeurIPS 2025)

Diversifying Counterattacks: Orthogonal Exploration for Robust CLIP Inference

Authors: Chengze Jiang, Minjing Dong, Xinli Shi, Jie Gui

Abstract: Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns about their reliability. Recent work, Test-Time Counterattack (TTC), improves robustness by generating perturbations that maximize the embedding deviation of adversarial inputs using PGD, pushing them away from their ad… ▽ More Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns about their reliability. Recent work, Test-Time Counterattack (TTC), improves robustness by generating perturbations that maximize the embedding deviation of adversarial inputs using PGD, pushing them away from their adversarial representations. However, due to the fundamental difference in optimization objectives between adversarial attacks and counterattacks, generating counterattacks solely based on gradients with respect to the adversarial input confines the search to a narrow space. As a result, the counterattacks could overfit limited adversarial patterns and lack the diversity to fully neutralize a broad range of perturbations. In this work, we argue that enhancing the diversity and coverage of counterattacks is crucial to improving adversarial robustness in test-time defense. Accordingly, we propose Directional Orthogonal Counterattack (DOC), which augments counterattack optimization by incorporating orthogonal gradient directions and momentum-based updates. This design expands the exploration of the counterattack space and increases the diversity of perturbations, which facilitates the discovery of more generalizable counterattacks and ultimately improves the ability to neutralize adversarial perturbations. Meanwhile, we present a directional sensitivity score based on averaged cosine similarity to boost DOC by improving example discrimination and adaptively modulating the counterattack strength. Extensive experiments on 16 datasets demonstrate that DOC improves adversarial robustness under various attacks while maintaining competitive clean accuracy. Code is available at https://github.com/bookman233/DOC. △ Less

Submitted 12 November, 2025; originally announced November 2025.

Comments: Accepted to AAAI-2026 Oral

A Unified Geometric Field Theory Framework for Transformers: From Manifold Embeddings to Kernel Modulation

Authors: Xianshuai Shi, Jianfeng Zhu, Leibo Liu

Abstract: The Transformer architecture has achieved tremendous success in natural language processing, computer vision, and scientific computing through its self-attention mechanism. However, its core components-positional encoding and attention mechanisms-have lacked a unified physical or mathematical interpretation. This paper proposes a structural theoretical framework that integrates positional encoding… ▽ More The Transformer architecture has achieved tremendous success in natural language processing, computer vision, and scientific computing through its self-attention mechanism. However, its core components-positional encoding and attention mechanisms-have lacked a unified physical or mathematical interpretation. This paper proposes a structural theoretical framework that integrates positional encoding, kernel integral operators, and attention mechanisms for in-depth theoretical investigation. We map discrete positions (such as text token indices and image pixel coordinates) to spatial functions on continuous manifolds, enabling a field-theoretic interpretation of Transformer layers as kernel-modulated operators acting over embedded manifolds. △ Less

Submitted 12 November, 2025; v1 submitted 11 November, 2025; originally announced November 2025.

Comments: Withdrawing to allow a significant revision and resubmission with improvements

PIMfused: Near-Bank DRAM-PIM with Fused-layer Dataflow for CNN Data Transfer Optimization

Authors: Simei Yang, Xinyu Shi, Lu Zhao, Yunyu Ling, Quanjun Wang, Francky Catthoor

Abstract: Near-bank Processing-in-Memory (PIM) architectures integrate processing cores (PIMcores) close to DRAM banks to mitigate the high cost of off-chip memory accesses. When accelerating convolutional neural network (CNN) on DRAM-PIM, performance is often constrained by cross-bank (or cross-PIMcore) data transfers, which are induced by the conventional layer-by-layer dataflow that enforces inter-bank (… ▽ More Near-bank Processing-in-Memory (PIM) architectures integrate processing cores (PIMcores) close to DRAM banks to mitigate the high cost of off-chip memory accesses. When accelerating convolutional neural network (CNN) on DRAM-PIM, performance is often constrained by cross-bank (or cross-PIMcore) data transfers, which are induced by the conventional layer-by-layer dataflow that enforces inter-bank (or inter-PIMcore) dependencies across successive CNN layers. To address this challenge, we propose PIMfused, a hardware-software co-design that enables fused-layer dataflow for end-to-end CNN execution in near-bank DRAM-PIM. By adopting fused-layer dataflow, PIMfused improves data reuse and, more importantly, breaks inter-bank data dependencies, thereby optimizing cross-bank data transfers without sacrificing bank-level parallelism. We study the impact of buffer sizes and PIMcore parallelism (1-bank vs. 4-bank) on PIMfused using end-to-end ResNet18. We present three key takeaways and show that with 4-bank PIMcores, PIMfused achieves overall PPA gains over a GDDR6-AiM-like baseline, cutting memory cycles to 30.6%, energy to 83.4%, and area to 76.5%. △ Less

Submitted 11 November, 2025; originally announced November 2025.

Comments: 6 pages

RelightMaster: Precise Video Relighting with Multi-plane Light Images

Authors: Weikang Bian, Xiaoyu Shi, Zhaoyang Huang, Jianhong Bai, Qinghe Wang, Xintao Wang, Pengfei Wan, Kun Gai, Hongsheng Li

Abstract: Recent advances in diffusion models enable high-quality video generation and editing, but precise relighting with consistent video contents, which is critical for shaping scene atmosphere and viewer attention, remains unexplored. Mainstream text-to-video (T2V) models lack fine-grained lighting control due to text's inherent limitation in describing lighting details and insufficient pre-training on… ▽ More Recent advances in diffusion models enable high-quality video generation and editing, but precise relighting with consistent video contents, which is critical for shaping scene atmosphere and viewer attention, remains unexplored. Mainstream text-to-video (T2V) models lack fine-grained lighting control due to text's inherent limitation in describing lighting details and insufficient pre-training on lighting-related prompts. Additionally, constructing high-quality relighting training data is challenging, as real-world controllable lighting data is scarce. To address these issues, we propose RelightMaster, a novel framework for accurate and controllable video relighting. First, we build RelightVideo, the first dataset with identical dynamic content under varying precise lighting conditions based on the Unreal Engine. Then, we introduce Multi-plane Light Image (MPLI), a novel visual prompt inspired by Multi-Plane Image (MPI). MPLI models lighting via K depth-aligned planes, representing 3D light source positions, intensities, and colors while supporting multi-source scenarios and generalizing to unseen light setups. Third, we design a Light Image Adapter that seamlessly injects MPLI into pre-trained Video Diffusion Transformers (DiT): it compresses MPLI via a pre-trained Video VAE and injects latent light features into DiT blocks, leveraging the base model's generative prior without catastrophic forgetting. Experiments show that RelightMaster generates physically plausible lighting and shadows and preserves original scene content. Demos are available at https://wkbian.github.io/Projects/RelightMaster/. △ Less

Submitted 9 November, 2025; originally announced November 2025.

Comments: Project Page: https://wkbian.github.io/Projects/RelightMaster/

Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language Navigation

Authors: Xiangyu Shi, Zerui Li, Yanyuan Qiao, Qi Wu

Abstract: Recent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. However, existing methods often rely on panoramic observations and two-stage pipelines involving waypoint predictors, which introduce significant latency and limit real-world applicability. In this work, we propose Fast-Smart… ▽ More Recent advances in Vision-and-Language Navigation in Continuous Environments (VLN-CE) have leveraged multimodal large language models (MLLMs) to achieve zero-shot navigation. However, existing methods often rely on panoramic observations and two-stage pipelines involving waypoint predictors, which introduce significant latency and limit real-world applicability. In this work, we propose Fast-SmartWay, an end-to-end zero-shot VLN-CE framework that eliminates the need for panoramic views and waypoint predictors. Our approach uses only three frontal RGB-D images combined with natural language instructions, enabling MLLMs to directly predict actions. To enhance decision robustness, we introduce an Uncertainty-Aware Reasoning module that integrates (i) a Disambiguation Module for avoiding local optima, and (ii) a Future-Past Bidirectional Reasoning mechanism for globally coherent planning. Experiments on both simulated and real-robot environments demonstrate that our method significantly reduces per-step latency while achieving competitive or superior performance compared to panoramic-view baselines. These results demonstrate the practicality and effectiveness of Fast-SmartWay for real-world zero-shot embodied navigation. △ Less

Submitted 2 November, 2025; originally announced November 2025.

Fusion of Multi-scale Heterogeneous Pathology Foundation Models for Whole Slide Image Analysis

Authors: Zhidong Yang, Xiuhui Shi, Wei Ba, Zhigang Song, Haijing Luan, Taiyuan Hu, Senlin Lin, Jiguang Wang, Shaohua Kevin Zhou, Rui Yan

Abstract: Whole slide image (WSI) analysis has emerged as an increasingly essential technique in computational pathology. Recent advances in the pathology foundation models (FMs) have demonstrated significant advantages in deriving meaningful patch-level or slide-level multi-scale features from WSIs. However, current pathology FMs have exhibited substantial heterogeneity caused by diverse private training d… ▽ More Whole slide image (WSI) analysis has emerged as an increasingly essential technique in computational pathology. Recent advances in the pathology foundation models (FMs) have demonstrated significant advantages in deriving meaningful patch-level or slide-level multi-scale features from WSIs. However, current pathology FMs have exhibited substantial heterogeneity caused by diverse private training datasets and different network architectures. This heterogeneity introduces performance variability when we utilize the features from different FMs in the downstream tasks. To fully explore the advantages of multiple FMs effectively, in this work, we propose a novel framework for the fusion of multi-scale heterogeneous pathology FMs, called FuseCPath, yielding a model with a superior ensemble performance. The main contributions of our framework can be summarized as follows: (i) To guarantee the representativeness of the training patches, we propose a multi-view clustering-based method to filter out the discriminative patches via multiple FMs' embeddings. (ii) To effectively fuse the patch-level FMs, we devise a cluster-level re-embedding strategy to online capture patch-level local features. (iii) To effectively fuse the slide-level FMs, we devise a collaborative distillation strategy to explore the connections between slide-level FMs. Extensive experiments demonstrate that the proposed FuseCPath achieves state-of-the-art performance across multiple tasks on diverse datasets. △ Less

Submitted 20 November, 2025; v1 submitted 31 October, 2025; originally announced October 2025.

Comments: 22 pages, 9 figures

Counteracting Matthew Effect in Self-Improvement of LVLMs through Head-Tail Re-balancing

Authors: Xin Guo, Zhiheng Xi, Yiwen Ding, Yitao Zhai, Xiaowei Shi, Xunliang Cai, Tao Gui, Qi Zhang, Xuanjing Huang

Abstract: Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision-language models (LVLMs), where models explore and learn from successful trajectories iteratively. However, we identify a critical issue during this process: the model excels at generating high-quality trajectories for simple queries (i.e., head data) but struggles with more complex ones (… ▽ More Self-improvement has emerged as a mainstream paradigm for advancing the reasoning capabilities of large vision-language models (LVLMs), where models explore and learn from successful trajectories iteratively. However, we identify a critical issue during this process: the model excels at generating high-quality trajectories for simple queries (i.e., head data) but struggles with more complex ones (i.e., tail data). This leads to an imbalanced optimization that drives the model to prioritize simple reasoning skills, while hindering its ability to tackle more complex reasoning tasks. Over iterations, this imbalance becomes increasingly pronounced--a dynamic we term the "Matthew effect"--which ultimately hinders further model improvement and leads to performance bottlenecks. To counteract this challenge, we introduce four efficient strategies from two perspectives: distribution-reshaping and trajectory-resampling, to achieve head-tail re-balancing during the exploration-and-learning self-improvement process. Extensive experiments on Qwen2-VL-7B-Instruct and InternVL2.5-4B models across visual reasoning tasks demonstrate that our methods consistently improve visual reasoning capabilities, outperforming vanilla self-improvement by 3.86 points on average. △ Less

Submitted 30 October, 2025; originally announced October 2025.

Comments: Preprint

VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning

Authors: Baolu Li, Yiming Zhang, Qinghe Wang, Liqian Ma, Xiaoyu Shi, Xintao Wang, Pengfei Wan, Zhenfei Yin, Yunzhi Zhuge, Huchuan Lu, Xu Jia

Abstract: Visual effects (VFX) are crucial to the expressive power of digital media, yet their creation remains a major challenge for generative AI. Prevailing methods often rely on the one-LoRA-per-effect paradigm, which is resource-intensive and fundamentally incapable of generalizing to unseen effects, thus limiting scalability and creation. To address this challenge, we introduce VFXMaster, the first un… ▽ More Visual effects (VFX) are crucial to the expressive power of digital media, yet their creation remains a major challenge for generative AI. Prevailing methods often rely on the one-LoRA-per-effect paradigm, which is resource-intensive and fundamentally incapable of generalizing to unseen effects, thus limiting scalability and creation. To address this challenge, we introduce VFXMaster, the first unified, reference-based framework for VFX video generation. It recasts effect generation as an in-context learning task, enabling it to reproduce diverse dynamic effects from a reference video onto target content. In addition, it demonstrates remarkable generalization to unseen effect categories. Specifically, we design an in-context conditioning strategy that prompts the model with a reference example. An in-context attention mask is designed to precisely decouple and inject the essential effect attributes, allowing a single unified model to master the effect imitation without information leakage. In addition, we propose an efficient one-shot effect adaptation mechanism to boost generalization capability on tough unseen effects from a single user-provided video rapidly. Extensive experiments demonstrate that our method effectively imitates various categories of effect information and exhibits outstanding generalization to out-of-domain effects. To foster future research, we will release our code, models, and a comprehensive dataset to the community. △ Less

Submitted 29 October, 2025; originally announced October 2025.

Comments: Project Page URL:https://libaolu312.github.io/VFXMaster/

U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching

Authors: Junsheng Zhou, Xingyu Shi, Haichuan Song, Yi Fang, Yu-Shen Liu, Zhizhong Han

Abstract: Point clouds captured by scanning sensors are often perturbed by noise, which have a highly negative impact on downstream tasks (e.g. surface reconstruction and shape understanding). Previous works mostly focus on training neural networks with noisy-clean point cloud pairs for learning denoising priors, which requires extensively manual efforts. In this work, we introduce U-CAN, an Unsupervised fr… ▽ More Point clouds captured by scanning sensors are often perturbed by noise, which have a highly negative impact on downstream tasks (e.g. surface reconstruction and shape understanding). Previous works mostly focus on training neural networks with noisy-clean point cloud pairs for learning denoising priors, which requires extensively manual efforts. In this work, we introduce U-CAN, an Unsupervised framework for point cloud denoising with Consistency-Aware Noise2Noise matching. Specifically, we leverage a neural network to infer a multi-step denoising path for each point of a shape or scene with a noise to noise matching scheme. We achieve this by a novel loss which enables statistical reasoning on multiple noisy point cloud observations. We further introduce a novel constraint on the denoised geometry consistency for learning consistency-aware denoising patterns. We justify that the proposed constraint is a general term which is not limited to 3D domain and can also contribute to the area of 2D image denoising. Our evaluations under the widely used benchmarks in point cloud denoising, upsampling and image denoising show significant improvement over the state-of-the-art unsupervised methods, where U-CAN also produces comparable results with the supervised methods. △ Less

Submitted 29 October, 2025; originally announced October 2025.

Comments: Accepted by NeurIPS 2025. Project page: https://gloriasze.github.io/U-CAN/

Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language Foundation

Authors: Ling Team, Ang Li, Ben Liu, Binbin Hu, Bing Li, Bingwei Zeng, Borui Ye, Caizhi Tang, Changxin Tian, Chao Huang, Chao Zhang, Chen Qian, Chenchen Ju, Chenchen Li, Chengfu Tang, Chilin Fu, Chunshao Ren, Chunwei Wu, Cong Zhang, Cunyin Peng, Dafeng Xu, Daixin Wang, Dalong Zhang, Dingnan Jin, Dingyuan Zhu , et al. (117 additional authors not shown)

Abstract: We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three… ▽ More We introduce Ling 2.0, a series reasoning-oriented language foundation built upon the principle that every activation boosts reasoning capability. Designed to scale from tens of billions to one trillion parameters under a unified Mixture-of-Experts (MoE) paradigm, Ling 2.0 emphasizes high sparsity, cross-scale consistency, and efficiency guided by empirical scaling laws. The series includes three non-thinking (instruct) models - Ling-mini-2.0, Ling-flash-2.0, and Ling-1T - ranging from 16B to 1T total parameters and achieving up to 7-fold active-compute efficiency compared with dense counterparts. Ling 2.0 integrates coordinated innovations across model architecture, pre-training, post-training, and infrastructure: a high-sparsity MoE with MTP for efficient reasoning, reasoning-oriented data and mid-training CoT activation, reinforcement-based fine-tuning (DFT, Evo-CoT), and full-scale FP8 training with fine-grained heterogeneous pipelines. At the trillion scale, Ling-1T establishes a new Pareto frontier of reasoning accuracy versus computational efficiency, demonstrating that sparse activation, when properly aligned with reasoning objectives, enables scalable and efficient intelligence. Collectively, Ling 2.0 provides a coherent, open, and efficient foundation for advancing future reasoning and thinking models, including the Ring series built upon the same base. △ Less

Submitted 6 November, 2025; v1 submitted 24 October, 2025; originally announced October 2025.

Comments: Ling 2.0 Technical Report

Conformal Lesion Segmentation for 3D Medical Images

Authors: Binyu Tan, Zhiyuan Wang, Jinhao Duan, Kaidi Xu, Heng Tao Shen, Xiaoshuang Shi, Fumin Shen

Abstract: Medical image segmentation serves as a critical component of precision medicine, enabling accurate localization and delineation of pathological regions, such as lesions. However, existing models empirically apply fixed thresholds (e.g., 0.5) to differentiate lesions from the background, offering no statistical guarantees on key metrics such as the false negative rate (FNR). This lack of principled… ▽ More Medical image segmentation serves as a critical component of precision medicine, enabling accurate localization and delineation of pathological regions, such as lesions. However, existing models empirically apply fixed thresholds (e.g., 0.5) to differentiate lesions from the background, offering no statistical guarantees on key metrics such as the false negative rate (FNR). This lack of principled risk control undermines their reliable deployment in high-stakes clinical applications, especially in challenging scenarios like 3D lesion segmentation (3D-LS). To address this issue, we propose a risk-constrained framework, termed Conformal Lesion Segmentation (CLS), that calibrates data-driven thresholds via conformalization to ensure the test-time FNR remains below a target tolerance $\varepsilon$ under desired risk levels. CLS begins by holding out a calibration set to analyze the threshold setting for each sample under the FNR tolerance, drawing on the idea of conformal prediction. We define an FNR-specific loss function and identify the critical threshold at which each calibration data point just satisfies the target tolerance. Given a user-specified risk level $α$, we then determine the approximate $1-α$ quantile of all the critical thresholds in the calibration set as the test-time confidence threshold. By conformalizing such critical thresholds, CLS generalizes the statistical regularities observed in the calibration set to new test data, providing rigorous FNR constraint while yielding more precise and reliable segmentations. We validate the statistical soundness and predictive performance of CLS on six 3D-LS datasets across five backbone models, and conclude with actionable insights for deploying risk-aware segmentation in clinical practice. △ Less

Submitted 19 October, 2025; originally announced October 2025.

Cerberus: Real-Time Video Anomaly Detection via Cascaded Vision-Language Models

Authors: Yue Zheng, Xiufang Shi, Jiming Chen, Yuanchao Shu

Abstract: Video anomaly detection (VAD) has rapidly advanced by recent development of Vision-Language Models (VLMs). While these models offer superior zero-shot detection capabilities, their immense computational cost and unstable visual grounding performance hinder real-time deployment. To overcome these challenges, we introduce Cerberus, a two-stage cascaded system designed for efficient yet accurate real… ▽ More Video anomaly detection (VAD) has rapidly advanced by recent development of Vision-Language Models (VLMs). While these models offer superior zero-shot detection capabilities, their immense computational cost and unstable visual grounding performance hinder real-time deployment. To overcome these challenges, we introduce Cerberus, a two-stage cascaded system designed for efficient yet accurate real-time VAD. Cerberus learns normal behavioral rules offline, and combines lightweight filtering with fine-grained VLM reasoning during online inference. The performance gains of Cerberus come from two key innovations: motion mask prompting and rule-based deviation detection. The former directs the VLM's attention to regions relevant to motion, while the latter identifies anomalies as deviations from learned norms rather than enumerating possible anomalies. Extensive evaluations on four datasets show that Cerberus on average achieves 57.68 fps on an NVIDIA L40S GPU, a 151.79$\times$ speedup, and 97.2\% accuracy comparable to the state-of-the-art VLM-based VAD methods, establishing it as a practical solution for real-time video analytics. △ Less

Submitted 17 October, 2025; originally announced October 2025.

SENTINEL: A Multi-Level Formal Framework for Safety Evaluation of LLM-based Embodied Agents

Authors: Simon Sinong Zhan, Yao Liu, Philip Wang, Zinan Wang, Qineng Wang, Zhian Ruan, Xiangyu Shi, Xinyu Cao, Frank Yang, Kangrui Wang, Huajie Shao, Manling Li, Qi Zhu

Abstract: We present Sentinel, the first framework for formally evaluating the physical safety of Large Language Model(LLM-based) embodied agents across the semantic, plan, and trajectory levels. Unlike prior methods that rely on heuristic rules or subjective LLM judgments, Sentinel grounds practical safety requirements in formal temporal logic (TL) semantics that can precisely specify state invariants, tem… ▽ More We present Sentinel, the first framework for formally evaluating the physical safety of Large Language Model(LLM-based) embodied agents across the semantic, plan, and trajectory levels. Unlike prior methods that rely on heuristic rules or subjective LLM judgments, Sentinel grounds practical safety requirements in formal temporal logic (TL) semantics that can precisely specify state invariants, temporal dependencies, and timing constraints. It then employs a multi-level verification pipeline where (i) at the semantic level, intuitive natural language safety requirements are formalized into TL formulas and the LLM agent's understanding of these requirements is probed for alignment with the TL formulas; (ii) at the plan level, high-level action plans and subgoals generated by the LLM agent are verified against the TL formulas to detect unsafe plans before execution; and (iii) at the trajectory level, multiple execution trajectories are merged into a computation tree and efficiently verified against physically-detailed TL specifications for a final safety check. We apply Sentinel in VirtualHome and ALFRED, and formally evaluate multiple LLM-based embodied agents against diverse safety requirements. Our experiments show that by grounding physical safety in temporal logic and applying verification methods across multiple levels, Sentinel provides a rigorous foundation for systematically evaluating LLM-based embodied agents in physical environments, exposing safety violations overlooked by previous methods and offering insights into their failure modes. △ Less

Submitted 14 October, 2025; originally announced October 2025.

Can Tool-Integrated Reinforcement Learning Generalize Across Diverse Domains?

Authors: Zhengyu Chen, Jinluan Yang, Teng Xiao, Ruochen Zhou, Luan Zhang, Xiangyu Xi, Xiaowei Shi, Wei Wang, Jinggang Wang

Abstract: Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains underexplored. In this work, we investigate the cross-domain generalization of an LLM agent equipped with a code interpreter tool, which is exclusively trained on mathema… ▽ More Recent advances in large language models (LLMs) have demonstrated remarkable capabilities in reasoning and tool utilization. However, the generalization of tool-augmented reinforcement learning (RL) across diverse domains remains underexplored. In this work, we investigate the cross-domain generalization of an LLM agent equipped with a code interpreter tool, which is exclusively trained on mathematical problem-solving tasks. Despite the restricted training domain, we evaluate the agent's performance across several distinct reasoning domains. The results reveal that RL-based tool usage learned from mathematical tasks can be effectively transferred to complex tasks in other domains, enabling great task performance and high token efficiency. To facilitate this cross-domain transfer, we propose a Tool Generalization Reinforcement Learning (TGRL) framework designed to promote domain-agnostic learning and skill migration, encompassing: (i) a standardized tool interface that abstracts domain-specific nuances through consistent formatting and explicit termination, fostering transferable invocation patterns; (ii) a dual-component reward system that decomposes rewards to incentivize generalizable behaviors like tool efficiency and reasoning abstraction, ensuring alignment and robustness across domain shifts; and (iii) an XML-based prompt template that separates thinking, tool calls, and responses to encourage modular, domain-invariant planning and coherent multi-turn interactions. Extensive experiments across diverse benchmarks validate our approach, achieving state-of-the-art performance and highlighting the cross-domain potential of Tool RL for LLM reasoning. △ Less

Submitted 13 October, 2025; originally announced October 2025.

Throughput Maximization for Multiuser Communications with Flexible-Sector 6DMA

Authors: Xiaoming Shi, Yunli Li, Xiaodan Shao, Jie Xu, Rui Zhang

Abstract: This paper presents a cost-effective and easily-deployable flexible-sector six-dimensional movable antenna (6DMA) architecture for future wireless communication networks, which enables flexible antenna configurations to match users' spatial distribution for capacity enhancement. Different from conventional sectorized base station (BS) with fixed-position antennas (FPAs), the flexible-sector 6DMA-e… ▽ More This paper presents a cost-effective and easily-deployable flexible-sector six-dimensional movable antenna (6DMA) architecture for future wireless communication networks, which enables flexible antenna configurations to match users' spatial distribution for capacity enhancement. Different from conventional sectorized base station (BS) with fixed-position antennas (FPAs), the flexible-sector 6DMA-enabled BS employs multiple directional sector antenna arrays that can flexibly move along a common circular track. By properly moving antennas across sectors and rotating all sector antenna arrays synchronously, the flexible-sector BS can adjust the coverage regions of all sectors with flexible antenna allocations over them. In particular, we consider the multiuser downlink communication employing the orthogonal multiple access (OMA) to serve users in each sector. Under this setup, we jointly optimize the sector rotation and the antenna allocation at the flexible-sector BS to maximize the average common throughput achievable for all users based on their spatial distribution. We solve this non-convex optimization problem by deriving closed-form solutions and thereby analyze the effect of users' spatial distribution on the achievable common throughput. It is shown that equal user distribution over sectors is optimal for maximizing the common throughput. Motivated by this result, we further develop a low-complexity suboptimal solution for the sector rotation that minimizes the variance of user numbers across sectors. Finally, we provide simulation results to verify our analytical results and validate the performance of our proposed solutions. It is demonstrated that the flexible-sector BS significantly improves the network throughput as compared to other benchmark schemes. △ Less

Submitted 12 October, 2025; originally announced October 2025.

A Survey of Inductive Reasoning for Large Language Models

Authors: Kedi Chen, Dezhao Ruan, Yuhao Dan, Yaoting Wang, Siyu Yan, Xuecheng Wu, Yinqi Zhang, Qin Chen, Jie Zhou, Liang He, Biqing Qi, Linyang Li, Qipeng Guo, Xiaoming Shi, Wei Zhang

Abstract: Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning,… ▽ More Reasoning is an important task for large language models (LLMs). Among all the reasoning paradigms, inductive reasoning is one of the fundamental types, which is characterized by its particular-to-general thinking process and the non-uniqueness of its answers. The inductive mode is crucial for knowledge generalization and aligns better with human cognition, so it is a fundamental mode of learning, hence attracting increasing interest. Despite the importance of inductive reasoning, there is no systematic summary of it. Therefore, this paper presents the first comprehensive survey of inductive reasoning for LLMs. First, methods for improving inductive reasoning are categorized into three main areas: post-training, test-time scaling, and data augmentation. Then, current benchmarks of inductive reasoning are summarized, and a unified sandbox-based evaluation approach with the observation coverage metric is derived. Finally, we offer some analyses regarding the source of inductive ability and how simple model architectures and data help with inductive tasks, providing a solid foundation for future research. △ Less

Submitted 11 October, 2025; originally announced October 2025.

Ctrl-World: A Controllable Generative World Model for Robot Manipulation

Authors: Yanjiang Guo, Lucy Xiaoyang Shi, Jianyu Chen, Chelsea Finn

Abstract: Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and diffic… ▽ More Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number of real-world rollouts, while systematic improvement demands additional corrective data with expert labels. Both of these processes are slow, costly, and difficult to scale. World models offer a promising, scalable alternative by enabling policies to rollout within imagination space. However, a key challenge is building a controllable world model that can handle multi-step interactions with generalist robot policies. This requires a world model compatible with modern generalist policies by supporting multi-view prediction, fine-grained action control, and consistent long-horizon interactions, which is not achieved by previous works. In this paper, we make a step forward by introducing a controllable multi-view world model that can be used to evaluate and improve the instruction-following ability of generalist robot policies. Our model maintains long-horizon consistency with a pose-conditioned memory retrieval mechanism and achieves precise action control through frame-level action conditioning. Trained on the DROID dataset (95k trajectories, 564 scenes), our model generates spatially and temporally consistent trajectories under novel scenarios and new camera placements for over 20 seconds. We show that our method can accurately rank policy performance without real-world robot rollouts. Moreover, by synthesizing successful trajectories in imagination and using them for supervised fine-tuning, our approach can improve policy success by 44.7\%. △ Less

Submitted 14 October, 2025; v1 submitted 11 October, 2025; originally announced October 2025.

Comments: 17 pages

AutoQual: An LLM Agent for Automated Discovery of Interpretable Features for Review Quality Assessment

Authors: Xiaochong Lan, Jie Feng, Yinxing Liu, Xinlei Shi, Yong Li

Abstract: Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, quality is a domain-dependent and dynamic concept, making its assessment a formidable challenge. Traditional methods relying on hand-crafted features are unscalable across domains and fail to adapt to evolving content patt… ▽ More Ranking online reviews by their intrinsic quality is a critical task for e-commerce platforms and information services, impacting user experience and business outcomes. However, quality is a domain-dependent and dynamic concept, making its assessment a formidable challenge. Traditional methods relying on hand-crafted features are unscalable across domains and fail to adapt to evolving content patterns, while modern deep learning approaches often produce black-box models that lack interpretability and may prioritize semantics over quality. To address these challenges, we propose AutoQual, an LLM-based agent framework that automates the discovery of interpretable features. While demonstrated on review quality assessment, AutoQual is designed as a general framework for transforming tacit knowledge embedded in data into explicit, computable features. It mimics a human research process, iteratively generating feature hypotheses through reflection, operationalizing them via autonomous tool implementation, and accumulating experience in a persistent memory. We deploy our method on a large-scale online platform with a billion-level user base. Large-scale A/B testing confirms its effectiveness, increasing average reviews viewed per user by 0.79% and the conversion rate of review readers by 0.27%. △ Less

Submitted 9 October, 2025; originally announced October 2025.

Comments: EMNLP 2025

AV-EMO-Reasoning: Benchmarking Emotional Reasoning Capabilities in Omni-modal LLMS with Audio-visual Cues

Authors: Krish Patel, Dingkun Zhou, Ajay Kankipati, Akshaj Gupta, Zeyi Austin Li, Mohul Shukla, Vibhor Narang, Sara Kofman, Zongli Ye, Grace Wang, Xiaoyu Shi, Tingle Li, Guan-Ting Lin, Kan Jen Cheng, Huang-Cheng Chou, Jiachen Lian, Gopala Anumanchipalli

Abstract: Emotions conveyed through voice and face shape engagement and context in human-AI interaction. Despite rapid progress in omni-modal large language models (LLMs), the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV-EMO-Reasoning, a benchmark designed to systematically assess emotional coherence in LLMs. The framework leverages a… ▽ More Emotions conveyed through voice and face shape engagement and context in human-AI interaction. Despite rapid progress in omni-modal large language models (LLMs), the holistic evaluation of emotional reasoning with audiovisual cues remains limited. To address this gap, we introduce AV-EMO-Reasoning, a benchmark designed to systematically assess emotional coherence in LLMs. The framework leverages a curated, single- and multi-turn synthetic audiovisual corpus with a real-world set and is assessed under continuous, categorical, and perceptual metrics. Experiments with leading LLMs show that visual cues reliably improve emotional coherence over audio-only baselines. Moreover, LLMs can leverage audio-visual cues to generate more emotion-aware speech. Models exhibit complementary strengths across metric families, indicating that automatic scores capture facets distinct from perceptual judgments. By releasing a systematic evaluation benchmark, AV-EMO-Reasoning offers a reproducible standard for evaluating emotion-aware dialogue and advances toward more natural, adaptive human-AI interaction. △ Less

Submitted 8 October, 2025; originally announced October 2025.

EigenScore: OOD Detection using Covariance in Diffusion Models

Authors: Shirin Shoushtari, Yi Wang, Xiao Shi, M. Salman Asif, Ulugbek S. Kamilov

Abstract: Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems in safety-sensitive domains. Diffusion models have recently emerged as powerful generative models, capable of capturing complex data distributions through iterative denoising. Building on this progress, recent work has explored their potential for OOD detection. We propose EigenScore, a new OOD dete… ▽ More Out-of-distribution (OOD) detection is critical for the safe deployment of machine learning systems in safety-sensitive domains. Diffusion models have recently emerged as powerful generative models, capable of capturing complex data distributions through iterative denoising. Building on this progress, recent work has explored their potential for OOD detection. We propose EigenScore, a new OOD detection method that leverages the eigenvalue spectrum of the posterior covariance induced by a diffusion model. We argue that posterior covariance provides a consistent signal of distribution shift, leading to larger trace and leading eigenvalues on OOD inputs, yielding a clear spectral signature. We further provide analysis explicitly linking posterior covariance to distribution mismatch, establishing it as a reliable signal for OOD detection. To ensure tractability, we adopt a Jacobian-free subspace iteration method to estimate the leading eigenvalues using only forward evaluations of the denoiser. Empirically, EigenScore achieves SOTA performance, with up to 5% AUROC improvement over the best baseline. Notably, it remains robust in near-OOD settings such as CIFAR-10 vs CIFAR-100, where existing diffusion-based methods often fail. △ Less

Submitted 8 October, 2025; originally announced October 2025.

Spatiotemporal Forecasting as Planning: A Model-Based Reinforcement Learning Approach with Generative World Models

Authors: Hao Wu, Yuan Gao, Xingjian Shi, Shuaipeng Li, Fan Xu, Fan Zhang, Zhihong Zhu, Weiyan Wang, Xiao Luo, Kun Wang, Xian Wu, Xiaomeng Huang

Abstract: To address the dual challenges of inherent stochasticity and non-differentiable metrics in physical spatiotemporal forecasting, we propose Spatiotemporal Forecasting as Planning (SFP), a new paradigm grounded in Model-Based Reinforcement Learning. SFP constructs a novel Generative World Model to simulate diverse, high-fidelity future states, enabling an "imagination-based" environmental simulation… ▽ More To address the dual challenges of inherent stochasticity and non-differentiable metrics in physical spatiotemporal forecasting, we propose Spatiotemporal Forecasting as Planning (SFP), a new paradigm grounded in Model-Based Reinforcement Learning. SFP constructs a novel Generative World Model to simulate diverse, high-fidelity future states, enabling an "imagination-based" environmental simulation. Within this framework, a base forecasting model acts as an agent, guided by a beam search-based planning algorithm that leverages non-differentiable domain metrics as reward signals to explore high-return future sequences. These identified high-reward candidates then serve as pseudo-labels to continuously optimize the agent's policy through iterative self-training, significantly reducing prediction error and demonstrating exceptional performance on critical domain metrics like capturing extreme events. △ Less

Submitted 9 October, 2025; v1 submitted 4 October, 2025; originally announced October 2025.

KVComm: Enabling Efficient LLM Communication through Selective KV Sharing

Authors: Xiangyu Shi, Marco Chiesa, Gerald Q. Maguire Jr., Dejan Kostic

Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent systems, where effective inter-model communication is crucial. Existing communication protocols either rely on natural language, incurring high inference costs and information loss, or on hidden states, which suffer from information concentration bias and inefficiency. To address these limitations, we propose KVComm, a novel com… ▽ More Large Language Models (LLMs) are increasingly deployed in multi-agent systems, where effective inter-model communication is crucial. Existing communication protocols either rely on natural language, incurring high inference costs and information loss, or on hidden states, which suffer from information concentration bias and inefficiency. To address these limitations, we propose KVComm, a novel communication framework that enables efficient communication between LLMs through selective sharing of KV pairs. KVComm leverages the rich information encoded in the KV pairs while avoiding the pitfalls of hidden states. We introduce a KV layer-wise selection strategy based on attention importance scores with a Gaussian prior to identify the most informative KV pairs for communication. Extensive experiments across diverse tasks and model pairs demonstrate that KVComm achieves comparable performance to the upper-bound method, which directly merges inputs to one model without any communication, while transmitting as few as 30\% of layers' KV pairs. Our study highlights the potential of KV pairs as an effective medium for inter-LLM communication, paving the way for scalable and efficient multi-agent systems. △ Less

Submitted 2 October, 2025; originally announced October 2025.

Flexible-Sector 6DMA Base Station: Modeling and Design

Authors: Yunli Li, Xiaoming Shi, Xiaodan Shao, Jie Xu, Rui Zhang

Abstract: Six-dimensional movable antenna (6DMA) has emerged as a promising new technology for future wireless networks, which can adaptively adjust the three-dimensional (3D) positions and 3D rotations of antennas/antenna arrays for performance enhancement. This paper proposes a novel cost-effective 6DMA-based base station (BS) architecture, termed the \textit{flexible-sector} BS, which allows the deployed… ▽ More Six-dimensional movable antenna (6DMA) has emerged as a promising new technology for future wireless networks, which can adaptively adjust the three-dimensional (3D) positions and 3D rotations of antennas/antenna arrays for performance enhancement. This paper proposes a novel cost-effective 6DMA-based base station (BS) architecture, termed the \textit{flexible-sector} BS, which allows the deployed antennas to flexibly rotate and move along a circular track, thus enabling common sector rotation and flexible antenna allocation across sectors to adapt to the spatial user distribution efficiently. In particular, we focus on the uplink transmission in a single-cell system, where the flexible-sector BS receives independent messages from multiple users. We introduce an angular-domain user distribution model, which captures the users' spatial clustering or hot-spot distribution effectively. Assuming the zero-forcing (ZF) based receiver applied at the BS to decode multiuser signals, we derive the average sum rate achievable for the users as a function of the common rotation of sectors and the antenna allocation over them. Moreover, we develop a two-step algorithm to jointly optimize the common sector rotation and antenna allocation to maximize the average sum rate of all users. It is shown that the optimal antenna number in each sector linearly increases with the number of users in it. It is also revealed that under the most favorable user distribution, the achievable sum rate gain increases in the order of $\log_{2}(B)$ in the regime of asymptotically large number of antennas, where $B$ denotes the number of sectors. Numerically results also show that as $B$ increases, the proposed flexible-sector BS achieves higher sum rate, and it outperforms other benchmark schemes, such as the traditional fixed-sector BS as well as the BS with sector rotation or antenna allocation optimization only. △ Less

Submitted 30 September, 2025; originally announced September 2025.