Mingyang Sun

Quan Yuan, Zhikun Zhang, Linkang Du et al.

Video recognition systems are increasingly being deployed in daily life, such as content recommendation and security monitoring. To enhance video recognition development, many institutions have released high-quality public datasets with open-source licenses for training advanced models. At the same time, these datasets are also susceptible to misuse and infringement. Dataset copyright auditing is an effective solution to identify such unauthorized use. However, existing dataset copyright solutions primarily focus on the image domain; the complex nature of video data leaves dataset copyright auditing in the video domain unexplored. Specifically, video data introduces an additional temporal dimension, which poses significant challenges to the effectiveness and stealthiness of existing methods. In this paper, we propose VICTOR, the first dataset copyright auditing approach for video recognition systems. We develop a general and stealthy sample modification strategy that enhances the output discrepancy of the target model. By modifying only a small proportion of samples (e.g., 1%), VICTOR amplifies the impact of published modified samples on the prediction behavior of the target models. Then, the difference in the model's behavior for published modified and unpublished original samples can serve as a key basis for dataset auditing. Extensive experiments on multiple models and datasets highlight the superiority of VICTOR. Finally, we show that VICTOR is robust in the presence of several perturbation mechanisms to the training videos or the target models.

Chao Shen, Zihan Guo, Xu Wan et al.

Growing renewable penetration introduces substantial uncertainty into power system operations, necessitating frequent adaptation of dispatch objectives and constraints and challenging expertise-intensive, near-real-time modeling workflows. Large Language Models (LLMs) provide a promising avenue for automating this process by translating natural-language (NL) operational requirements into executable optimization models via semantic reasoning and code synthesis. Yet existing LLM datasets and benchmarks for optimization modeling primarily target coarse-grained cross-domain generalization, offering limited, rigorous evaluation in power-system settings, particularly for Optimal Power Flow (OPF). We therefore introduce \textbf{ProOPF-D} and \textbf{ProOPF-B}, a dataset and benchmark for professional-grade OPF modeling: ProOPF-D contains 12K instances pairing NL requests with parameter adjustments and structural extensions to a canonical OPF, together with executable implementations; ProOPF-B provides 121 expert-annotated test cases with ground-truth code, enabling end-to-end evaluation under both concrete and abstract OPF modeling regimes.

Xu Wan, Speed Zhu, Jianwei Cai et al.

Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets. In this work, we formulate inference budget allocation as a global constrained optimization problem governed by economic principles. By modeling per-query reasoning utility with a shifted-surge function, we derive an optimal allocation policy based on a global shadow price that equilibrates marginal utility under resource scarcity. Based on this theory, we propose Constrained Latent-utility Equilibrium Allocation for Reasoning (CLEAR). It performs rational abandonment and reallocates resources from insolvent queries to solvable queries near their emergence thresholds. Extensive experiments on several reasoning tasks with different traffic streams demonstrate that CLEAR significantly improves the Pareto frontier of total token cost versus mean accuracy. In resource-scarce regimes, CLEAR achieves up to a 3x improvement in global accuracy compared to uniform allocation.

Linkang Du, Min Chen, Mingyang Sun et al.

Data is a critical asset in AI, as high-quality datasets can significantly improve the performance of machine learning models. In safety-critical domains such as autonomous vehicles, offline deep reinforcement learning (offline DRL) is frequently used to train models on pre-collected datasets, as opposed to training these models by interacting with the real-world environment as the online DRL. To support the development of these models, many institutions make datasets publicly available with opensource licenses, but these datasets are at risk of potential misuse or infringement. Injecting watermarks to the dataset may protect the intellectual property of the data, but it cannot handle datasets that have already been published and is infeasible to be altered afterward. Other existing solutions, such as dataset inference and membership inference, do not work well in the offline DRL scenario due to the diverse model behavior characteristics and offline setting constraints. In this paper, we advocate a new paradigm by leveraging the fact that cumulative rewards can act as a unique identifier that distinguishes DRL models trained on a specific dataset. To this end, we propose ORL-AUDITOR, which is the first trajectory-level dataset auditing mechanism for offline RL scenarios. Our experiments on multiple offline DRL models and tasks reveal the efficacy of ORL-AUDITOR, with auditing accuracy over 95% and false positive rates less than 2.88%. We also provide valuable insights into the practical implementation of ORL-AUDITOR by studying various parameter settings. Furthermore, we demonstrate the auditing capability of ORL-AUDITOR on open-source datasets from Google and DeepMind, highlighting its effectiveness in auditing published datasets. ORL-AUDITOR is open-sourced at https://github.com/link-zju/ORL-Auditor.

Xiao Zhao, Bo Chen, Mingyang Sun et al.

Vision-based 3D semantic scene completion (SSC) describes autonomous driving scenes through 3D volume representations. However, the occlusion of invisible voxels by scene surfaces poses challenges to current SSC methods in hallucinating refined 3D geometry. This paper proposes HybridOcc, a hybrid 3D volume query proposal method generated by Transformer framework and NeRF representation and refined in a coarse-to-fine SSC prediction framework. HybridOcc aggregates contextual features through the Transformer paradigm based on hybrid query proposals while combining it with NeRF representation to obtain depth supervision. The Transformer branch contains multiple scales and uses spatial cross-attention for 2D to 3D transformation. The newly designed NeRF branch implicitly infers scene occupancy through volume rendering, including visible and invisible voxels, and explicitly captures scene depth rather than generating RGB color. Furthermore, we present an innovative occupancy-aware ray sampling method to orient the SSC task instead of focusing on the scene surface, further improving the overall performance. Extensive experiments on nuScenes and SemanticKITTI datasets demonstrate the effectiveness of our HybridOcc on the SSC task.

Mingyang Sun, Dingkang Yang, Dongliang Kou et al.

A human 3D avatar is one of the important elements in the metaverse, and the modeling effect directly affects people's visual experience. However, the human body has a complex topology and diverse details, so it is often expensive, time-consuming, and laborious to build a satisfactory model. Recent studies have proposed a novel method, implicit neural representation, which is a continuous representation method and can describe objects with arbitrary topology at arbitrary resolution. Researchers have applied implicit neural representation to human 3D avatar modeling and obtained more excellent results than traditional methods. This paper comprehensively reviews the application of implicit neural representation in human body modeling. First, we introduce three implicit representations of occupancy field, SDF, and NeRF, and make a classification of the literature investigated in this paper. Then the application of implicit modeling methods in the body, hand, and head are compared and analyzed respectively. Finally, we point out the shortcomings of current work and provide available suggestions for researchers.

Xiao Zhao, Xukun Zhang, Dingkang Yang et al.

Accurate and robust multimodal multi-task perception is crucial for modern autonomous driving systems. However, current multimodal perception research follows independent paradigms designed for specific perception tasks, leading to a lack of complementary learning among tasks and decreased performance in multi-task learning (MTL) due to joint training. In this paper, we propose MaskBEV, a masked attention-based MTL paradigm that unifies 3D object detection and bird's eye view (BEV) map segmentation. MaskBEV introduces a task-agnostic Transformer decoder to process these diverse tasks, enabling MTL to be completed in a unified decoder without requiring additional design of specific task heads. To fully exploit the complementary information between BEV map segmentation and 3D object detection tasks in BEV space, we propose spatial modulation and scene-level context aggregation strategies. These strategies consider the inherent dependencies between BEV segmentation and 3D detection, naturally boosting MTL performance. Extensive experiments on nuScenes dataset show that compared with previous state-of-the-art MTL methods, MaskBEV achieves 1.3 NDS improvement in 3D object detection and 2.7 mIoU improvement in BEV map segmentation, while also demonstrating slightly leading inference speed.

Hao Wang, Zeyu Gao, Chao Zhang et al.

Binary code representation learning has shown significant performance in binary analysis tasks. But existing solutions often have poor transferability, particularly in few-shot and zero-shot scenarios where few or no training samples are available for the tasks. To address this problem, we present CLAP (Contrastive Language-Assembly Pre-training), which employs natural language supervision to learn better representations of binary code (i.e., assembly code) and get better transferability. At the core, our approach boosts superior transfer learning capabilities by effectively aligning binary code with their semantics explanations (in natural language), resulting a model able to generate better embeddings for binary code. To enable this alignment training, we then propose an efficient dataset engine that could automatically generate a large and diverse dataset comprising of binary code and corresponding natural language explanations. We have generated 195 million pairs of binary code and explanations and trained a prototype of CLAP. The evaluations of CLAP across various downstream tasks in binary analysis all demonstrate exceptional performance. Notably, without any task-specific training, CLAP is often competitive with a fully supervised baseline, showing excellent transferability. We release our pre-trained model and code at https://github.com/Hustcw/CLAP.

Mingyang Sun, Pengxiang Ding, Weinan Zhang et al.

Diffusion policies have shown promise in learning complex behaviors from demonstrations, particularly for tasks requiring precise control and long-term planning. However, they face challenges in robustness when encountering distribution shifts. This paper explores improving diffusion-based imitation learning models through online interactions with the environment. We propose OTPR (Optimal Transport-guided score-based diffusion Policy for Reinforcement learning fine-tuning), a novel method that integrates diffusion policies with RL using optimal transport theory. OTPR leverages the Q-function as a transport cost and views the policy as an optimal transport map, enabling efficient and stable fine-tuning. Moreover, we introduce masked optimal transport to guide state-action matching using expert keypoints and a compatibility-based resampling strategy to enhance training stability. Experiments on three simulation tasks demonstrate OTPR's superior performance and robustness compared to existing methods, especially in complex and sparse-reward environments. In sum, OTPR provides an effective framework for combining IL and RL, achieving versatile and reliable policy learning. The code will be released at https://github.com/Sunmmyy/OTPR.git.

Hongwei Zhen, Ze Yu, Xin Xiang et al.

Power electronics systems are increasingly exposed to cyber threats due to their integration with digital controllers and communication networks. However, an attacker-oriented metric is still lacking to quantify the extent to which a node can be pushed toward instability within a privilege-constrained action space. This letter proposes an impedance-based Attack Reachable Domain (ARD) framework that maps feasible adversarial actions to critical-eigenvalue migration through impedance reshaping. Based on the ARD, an Attack Penetration Index is defined to quantify node-level cyber-vulnerability by jointly characterizing the penetration of the nominal stability margin and the accessibility of successful destabilizing attacks within a privilege-constrained action space. To make the proposed assessment computable when inverter models are unavailable, a practical gray-box workflow is further established by integrating existing impedance identification and differentiable surrogate tools. Case studies on a 4-bus system and a modified IEEE 39-bus system show that coordinated cross-layer manipulations are markedly more damaging than isolated single-layer attacks, and that the proposed metric reveals vulnerability patterns that cannot be inferred from grid-strength indicators.

Hongwei Zhen, Ze Yu, Xin Xiang et al.

The high penetration of voltage source converters in modern smart microgrids enhances operational flexibility while introducing complex cyber-physical vulnerabilities. Existing cyber-attack studies either require detailed knowledge of system topology and controller dynamics or depend on repeated online interactions, which may compromise practicality by generating operationally infeasible or limit-violating commands. This article investigates a dispatch command manipulation attack and develops an admittance-guided framework to identify the vulnerable inverter and the worst-case dispatch command that most severely degrades system stability. A compromised inverter is utilized to inject controlled harmonic perturbations for sparse admittance measurement, and a physics-informed neural network is then employed to reconstruct the operating-point-dependent admittance of target inverters over the feasible dispatch region. Based on the reconstructed admittance, a stability-margin-oriented optimization is formulated to locate the most vulnerable inverter and the corresponding worst-case dispatch command. Controller hardware-in-the-loop experiments on a five-inverter microgrid demonstrate that the identified command can drive the system into severe sub-synchronous oscillations while remaining within nominal dispatch bounds, highlighting the need for stability-aware command screening beyond static limit checking.

Miho Koda, Yu Zheng, Ruixian Ma et al.

Recent advances in large language models (LLMs), particularly those enhanced through reinforced post-training, have demonstrated impressive reasoning capabilities, as exemplified by models such as OpenAI o1 and DeepSeek-R1. However, these capabilities are predominantly benchmarked on domains like mathematical problem solving and code generation, leaving open the question of whether such reasoning skills generalize to complex real-world scenarios. In this paper, we introduce LocationReasoner, a benchmark designed to evaluate LLMs' reasoning abilities in the context of real-world site selection, where models must identify feasible locations by reasoning over diverse and complicated spatial, environmental, and logistic constraints. The benchmark covers carefully crafted queries of varying difficulty levels and is supported by a sandbox environment with in-house tools for constraint-based location search. Automated verification further guarantees the scalability of the benchmark, enabling the addition of arbitrary number of queries. Extensive evaluations on real-world site selection data from Boston, New York, and Tampa reveal that state-of-the-art reasoning models offer limited improvement over their non-reasoning predecessors in real-world contexts, with even the latest OpenAI o4 model failing on 30% of site selection tasks. Moreover, agentic strategies such as ReAct and Reflexion often suffer from over-reasoning, leading to worse outcomes than direct prompting. With key limitations of LLMs in holistic and non-linear reasoning highlighted, we release LocationReasoner to foster the development of LLMs and agents capable of robust, grounded reasoning in real-world decision-making tasks. Codes and data for our benchmark are available at https://github.com/miho-koda/LocationReasoner.

Xin Lu, Jing Qiu, Jiafeng Lin et al.

Emerging connect-and-manage practices allow new transmission-connected mega-loads to connect while enforcing time-varying admissible power exchange limits at the point of common coupling (PCC) in real time. Hyperscale artificial intelligence data centers (AIDCs), whose demand can reach hundreds of megawatts and whose internal computing-cooling dynamics evolve rapidly, can therefore face frequent conflicts between workload continuity requirements and externally imposed PCC envelopes. This paper proposes a battery-assisted operational framework in which on-site battery energy storage (BESS) serves as a physical buffering interface to reconcile fast internal dynamics with time-varying interconnection limits. A continuity-aware energy-computation model is developed to jointly capture checkpoint-constrained AI training workloads, information technology (IT) computing power-throughput characteristics, and IT-cooling thermal dynamics. A two-stage decision framework is then formulated, consisting of scenario-based day-ahead workload commitment and a real-time receding-horizon delivery assurance controller that enforces battery, thermal, and grid-interaction constraints. Case studies on the IEEE 39-bus system with Australian real data demonstrate that BESS substantially increases credible day-ahead workload commitment and improves real-time delivery robustness under transmission congestion. Sensitivity analyses further reveal a regime-dependent role transition of BESS -- from feasibility-oriented continuity support when PCC limits are binding to economy-driven flexibility provision as transmission constraints are relaxed.

Zhong Li, Zihan Guo, Xiaohan Lu et al.

Large language models (LLMs) are increasingly used to translate natural-language optimization problems into mathematical formulations and solver code, but matching the reference objective value is not a reliable test of correctness: an artifact may agree numerically while still changing the underlying optimization semantics. We formulate this issue as \emph{optimization-modeling hallucination detection}, namely structural consistency auditing over the problem description, symbolic model, and solver implementation. We develop, to our knowledge, the first fine-grained hallucination taxonomy specifically for optimization modeling, spanning objective, variable, constraint, and implementation failures. We use this taxonomy to design OptArgus, a multi-agent detector with conductor routing, specialist auditors, and evidence consolidation. To evaluate this setting, we introduce a three-part benchmark suite with $484$ clean artifacts, $1266$ controlled injected artifacts, and $6292$ natural LLM-generated artifacts. Against a matched single-agent baseline, OptArgus produces fewer false alarms on clean artifacts, more accurate top-ranked localization on controlled single-error cases, and stronger detection on natural model outputs. Together, these contributions turn optimization-modeling hallucination detection into a concrete empirical problem and suggest that modular, taxonomy-grounded auditing is a practical route to more reliable optimization modeling.

Chao Shen, Ke Zuo, Mingyang Sun

Existing dynamics prediction frameworks for transient stability analysis (TSA) fail to achieve multi-scenario "universality"--the inherent ability of a single, pre-trained architecture to generalize across diverse operating conditions, unseen faults, and heterogeneous systems. To address this, this paper proposes TSA-LLM, a large language model (LLM)-based universal framework that models multi-variate transient dynamics prediction as a univariate generative task with three key innovations: First, a novel data processing pipeline featuring channel independence decomposition to resolve dimensional heterogeneity, sample-wise normalization to eliminate separate stable or unstable pipelines, and temporal patching for efficient long-sequence modeling; Second, a parameter-efficient freeze-and-finetune strategy that augments the LLM's architecture with dedicated input embedding and output projection layers while freezing core transformer blocks to preserve generic feature extraction capabilities; Third, a two-stage fine-tuning scheme that combines teacher forcing, which feeds the model ground-truth data during initial training, with scheduled sampling, which gradually shifts to leveraging model-generated predictions, to mitigate cumulative errors in long-horizon iterative prediction. Comprehensive testing demonstrates the framework's universality, as TSA-LLM trained solely on the New England 39-bus system achieves zero-shot generalization to mixed stability conditions and unseen faults, and matches expert performance on the larger Iceland 189-bus system with only 5% fine-tuning data. This multi-scenario versatility validates a universal framework that eliminates scenario-specific retraining and achieves scalability via large-scale parameters and cross-scenario training data.

Zongyan Zhang, Chao Shen, Xu Wan et al.

The increasing penetration of renewable generation and the growing variability of electrified demand introduce substantial operational uncertainty to modern power systems. Topology reconfiguration is widely recognized as an effective and economical means to enhance grid resilience. Due to the coexistence of AC power-flow constraints and discrete switching decisions, topology reconfiguration in large-scale systems leads to a highly nonlinear and nonconvex optimization problem, making traditional methods computationally prohibitive. Consequently, several studies have explored reinforcement learning-based approaches to improve scalability and operational efficiency. However, its practical implementation is challenged by the high-dimensional combinatorial action space and the need to ensure safety during learning-based decision-making. To address these challenges, this paper presents a safe and intelligent topology control framework that integrates Large Language Models (LLMs) with a Safety Soft Actor-Critic (Safety-SAC) architecture. Operational voltage and thermal limits are reformulated into smooth safety-cost signals, enabling risk-aware policy optimization within a constrained Markov decision process. A knowledge-based Safety-LLM module is further introduced to refine unsafe or suboptimal transitions through domain knowledge and state-informed reasoning, thus guiding the learning agent toward safer and more effective switching actions. Experiments on the IEEE 36-bus and 118-bus Grid2Op benchmarks show that the proposed method consistently improves reward, survival time, and safety metrics, achieving higher reward, longer survival, and lower safety cost compared with SAC, ACE, and their safety-enhanced variants. These results demonstrate the potential of combining LLM-based reasoning with safe reinforcement learning to achieve scalable and reliable grid topology control.

Jianning Chi, Zelan Li, Geng Lin et al.

Weakly supervised segmentation methods can delineate thyroid nodules in ultrasound images efficiently using training data with coarse labels, but suffer from: 1) low-confidence pseudo-labels that follow topological priors, introducing significant label noise, and 2) low-rationality loss functions that rigidly compare segmentation with labels, ignoring discriminative information for nodules with diverse and complex shapes. To solve these issues, we clarify the objective and references for weakly supervised ultrasound image segmentation, presenting a framework with high-confidence pseudo-labels to represent topological and anatomical information and high-rationality losses to capture multi-level discriminative features. Specifically, we fuse geometric transformations of four-point annotations and MedSAM model results prompted by specific annotations to generate high-confidence box, foreground, and background labels. Our high-rationality learning strategy includes: 1) Alignment loss measuring spatial consistency between segmentation and box label, and topological continuity within the foreground label, guiding the network to perceive nodule location; 2) Contrastive loss pulling features from labeled foreground regions while pushing features from labeled foreground and background regions, guiding the network to learn nodule and background feature distribution; 3) Prototype correlation loss measuring consistency between correlation maps derived by comparing features with foreground and background prototypes, refining uncertain regions to accurate nodule edges. Experimental results show that our method achieves state-of-the-art performance on the TN3K and DDTI datasets. The code is available at https://github.com/bluehenglee/MLI-MSC.

Xu Wan, Chao Yang, Cheng Yang et al.

Safe Reinforcement Learning (RL) is crucial for achieving high performance while ensuring safety in real-world applications. However, the complex interplay of multiple uncertainty sources in real environments poses significant challenges for interpretable risk assessment and robust decision-making. To address these challenges, we propose Fuz-RL, a fuzzy measure-guided robust framework for safe RL. Specifically, our framework develops a novel fuzzy Bellman operator for estimating robust value functions using Choquet integrals. Theoretically, we prove that solving the Fuz-RL problem (in Constrained Markov Decision Process (CMDP) form) is equivalent to solving distributionally robust safe RL problems (in robust CMDP form), effectively avoiding min-max optimization. Empirical analyses on safe-control-gym and safety-gymnasium scenarios demonstrate that Fuz-RL effectively integrates with existing safe RL baselines in a model-free manner, significantly improving both safety and control performance under various types of uncertainties in observation, action, and dynamics.

Xu Wan, Yansheng Wang, Wenqi Huang et al.

Traditional on-policy Reinforcement Learning with Verifiable Rewards (RLVR) frameworks suffer from experience waste and reward homogeneity, which directly hinders learning efficiency on difficult samples during large language models post-training. In this paper, we introduce Batch Adaptation Policy Optimization (BAPO), an off-policy RLVR framework to improve the data efficiency in large language models post-training. It dynamically selects training batches by re-evaluating historically difficult samples and reusing high-quality ones, while holding a lower bound guarantee for policy improvement. Extensive experiments further demonstrate that BAPO achieves an average 12.5% improvement over GRPO across mathematics, planning, and visual reasoning tasks. Crucially, BAPO successfully resolves 40.7% of problems that base models consistently fail to solve.

Mingcheng Li, Dingkang Yang, Xiao Zhao et al.

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. Most MSA efforts are based on the assumption of modality completeness. However, in real-world applications, some practical factors cause uncertain modality missingness, which drastically degrades the model's performance. To this end, we propose a Correlation-decoupled Knowledge Distillation (CorrKD) framework for the MSA task under uncertain missing modalities. Specifically, we present a sample-level contrastive distillation mechanism that transfers comprehensive knowledge containing cross-sample correlations to reconstruct missing semantics. Moreover, a category-guided prototype distillation mechanism is introduced to capture cross-category correlations using category prototypes to align feature distributions and generate favorable joint representations. Eventually, we design a response-disentangled consistency distillation strategy to optimize the sentiment decision boundaries of the student network through response disentanglement and mutual information maximization. Comprehensive experiments on three datasets indicate that our framework can achieve favorable improvements compared with several baselines.

Zhefei Gong, Pengxiang Ding, Shangke Lyu et al.

In robotic visuomotor policy learning, diffusion-based models have achieved significant success in improving the accuracy of action trajectory generation compared to traditional autoregressive models. However, they suffer from inefficiency due to multiple denoising steps and limited flexibility from complex constraints. In this paper, we introduce Coarse-to-Fine AutoRegressive Policy (CARP), a novel paradigm for visuomotor policy learning that redefines the autoregressive action generation process as a coarse-to-fine, next-scale approach. CARP decouples action generation into two stages: first, an action autoencoder learns multi-scale representations of the entire action sequence; then, a GPT-style transformer refines the sequence prediction through a coarse-to-fine autoregressive process. This straightforward and intuitive approach produces highly accurate and smooth actions, matching or even surpassing the performance of diffusion-based policies while maintaining efficiency on par with autoregressive policies. We conduct extensive evaluations across diverse settings, including single-task and multi-task scenarios on state-based and image-based simulation benchmarks, as well as real-world tasks. CARP achieves competitive success rates, with up to a 10% improvement, and delivers 10x faster inference compared to state-of-the-art policies, establishing a high-performance, efficient, and flexible paradigm for action generation in robotic tasks.

Yang Liu, Ming Ma, Xiaomin Yu et al.

Despite impressive advancements in Visual-Language Models (VLMs) for multi-modal tasks, their reliance on RGB inputs limits precise spatial understanding. Existing methods for integrating spatial cues, such as point clouds or depth, either require specialized sensors or fail to effectively exploit depth information for higher-order reasoning. To this end, we propose a novel Spatial Sense and Reasoning method, dubbed SSR, a novel framework that transforms raw depth data into structured, interpretable textual rationales. These textual rationales serve as meaningful intermediate representations to significantly enhance spatial reasoning capabilities. Additionally, we leverage knowledge distillation to compress the generated rationales into compact latent embeddings, which facilitate resource-efficient and plug-and-play integration into existing VLMs without retraining. To enable comprehensive evaluation, we introduce a new dataset named SSR-CoT, a million-scale visual-language reasoning dataset enriched with intermediate spatial reasoning annotations, and present SSRBench, a comprehensive multi-task benchmark. Extensive experiments on multiple benchmarks demonstrate SSR substantially improves depth utilization and enhances spatial reasoning, thereby advancing VLMs toward more human-like multi-modal understanding. Project page: https://yliu-cs.github.io/SSR.

Xinyang Tong, Pengxiang Ding, Yiguo Fan et al.

This paper addresses the inherent inference latency challenges associated with deploying multimodal large language models (MLLM) in quadruped vision-language-action (QUAR-VLA) tasks. Our investigation reveals that conventional parameter reduction techniques ultimately impair the performance of the language foundation model during the action instruction tuning phase, making them unsuitable for this purpose. We introduce a novel latency-free quadruped MLLM model, dubbed QUART-Online, designed to enhance inference efficiency without degrading the performance of the language foundation model. By incorporating Action Chunk Discretization (ACD), we compress the original action representation space, mapping continuous action values onto a smaller set of discrete representative vectors while preserving critical information. Subsequently, we fine-tune the MLLM to integrate vision, language, and compressed actions into a unified semantic space. Experimental results demonstrate that QUART-Online operates in tandem with the existing MLLM system, achieving real-time inference in sync with the underlying controller frequency, significantly boosting the success rate across various tasks by 65%. Our project page is https://quart-online.github.io.

Mingcheng Li, Dingkang Yang, Yang Liu et al.

Multimodal Sentiment Analysis (MSA) is an important research area that aims to understand and recognize human sentiment through multiple modalities. The complementary information provided by multimodal fusion promotes better sentiment analysis compared to utilizing only a single modality. Nevertheless, in real-world applications, many unavoidable factors may lead to situations of uncertain modality missing, thus hindering the effectiveness of multimodal modeling and degrading the model's performance. To this end, we propose a Hierarchical Representation Learning Framework (HRLF) for the MSA task under uncertain missing modalities. Specifically, we propose a fine-grained representation factorization module that sufficiently extracts valuable sentiment information by factorizing modality into sentiment-relevant and modality-specific representations through crossmodal translation and sentiment semantic reconstruction. Moreover, a hierarchical mutual information maximization mechanism is introduced to incrementally maximize the mutual information between multi-scale representations to align and reconstruct the high-level semantics in the representations. Ultimately, we propose a hierarchical adversarial learning mechanism that further aligns and adapts the latent distribution of sentiment-relevant representations to produce robust joint multimodal representations. Comprehensive experiments on three datasets demonstrate that HRLF significantly improves MSA performance under uncertain modality missing cases.

Bofang Jia, Pengxiang Ding, Can Cui et al.

Visual-motor policy learning has advanced with architectures like diffusion-based policies, known for modeling complex robotic trajectories. However, their prolonged inference times hinder high-frequency control tasks requiring real-time feedback. While consistency distillation (CD) accelerates inference, it introduces errors that compromise action quality. To address these limitations, we propose the Score and Distribution Matching Policy (SDM Policy), which transforms diffusion-based policies into single-step generators through a two-stage optimization process: score matching ensures alignment with true action distributions, and distribution matching minimizes KL divergence for consistency. A dual-teacher mechanism integrates a frozen teacher for stability and an unfrozen teacher for adversarial training, enhancing robustness and alignment with target distributions. Evaluated on a 57-task simulation benchmark, SDM Policy achieves a 6x inference speedup while having state-of-the-art action quality, providing an efficient and reliable framework for high-frequency robotic tasks.

Xu Wan, Wei Wang, Wenyue Xu et al.

Reinforcement Learning (RL)-based post-training has significantly advanced the complex reasoning capabilities of language models, fostering sophisticated self-reflection processes. However, this ``slow thinking'' paradigm presents a critical challenge to reasoning efficiency: models may expend excessive computation on simple questions and shift reasoning prematurely for complex ones. Previous mechanisms typically rely on static length budgets or predefined rules, lacking the adaptability for varying question complexities and models' evolving capabilities. To this end, we propose AdapThink, an adaptive post-training framework designed to induce more efficient thinking while maintaining the performance of reasoning language models. Specifically, AdapThink incorporates two key mechanisms: 1) A group-relative reward function that leverages model confidence and response's characteristic to dynamically adjust the preference of reflection-related transition words without resorting to a fixed length preference. 2) A diversity-aware sampling mechanism that balances the training group's solution accuracy with reasoning diversity via an entropy-guided score. Experiments on several mathematical reasoning datasets with DeepSeek-distilled models demonstrate AdapThink's advantages in enabling adaptive reasoning patterns and mitigating the inefficiencies.

Hengtao Li, Pengxiang Ding, Runze Suo et al.

Vision-Language-Action (VLA) models enable embodied decision-making but rely heavily on imitation learning, leading to compounding errors and poor robustness under distribution shift. Reinforcement learning (RL) can mitigate these issues yet typically demands costly real-world interactions or suffers from sim-to-real gaps. We introduce VLA-RFT, a reinforcement fine-tuning framework that leverages a data-driven world model as a controllable simulator. Trained from real interaction data, the simulator predicts future visual observations conditioned on actions, allowing policy rollouts with dense, trajectory-level rewards derived from goal-achieving references. This design delivers an efficient and action-aligned learning signal, drastically lowering sample requirements. With fewer than 400 fine-tuning steps, VLA-RFT surpasses strong supervised baselines and achieves greater efficiency than simulator-based RL. Moreover, it exhibits strong robustness under perturbed conditions, sustaining stable task execution. Our results establish world-model-based RFT as a practical post-training paradigm to enhance the generalization and robustness of VLA models. For more details, please refer to https://vla-rft.github.io/.

Xu Wan, Wenyue Xu, Chao Yang et al.

Recent advancements in Large Language Models (LLMs) and Reinforcement Learning (RL) have shown significant promise in decision-making tasks. Nevertheless, for large-scale industrial decision problems, both approaches face distinct challenges: LLMs lack real-time long-sequence decision-making capabilities, while RL struggles with sample efficiency in vast action spaces. To bridge this gap, we propose Agents Co-Evolution (ACE), a synergistic framework between LLMs and RL agents for large-scale decision-making scenarios. ACE introduces a dual-role trajectory refinement mechanism where LLMs act as both Policy Actor and Value Critic during RL's training: the Actor refines suboptimal actions via multi-step reasoning and environment validation, while the Critic performs temporal credit assignment through trajectory-level reward shaping. Concurrently, RL agent enhances LLMs' task-specific decision-making with high-quality fine-tuning datasets generated via prioritized experience replay. Through extensive experiments across multiple power grid operation challenges with action spaces exceeding 60K discrete actions, ACE demonstrates superior performance over existing RL methods and LLM-based methods.

Xu Wan, Chao Yang, Cheng Yang et al.

Although multi-agent reinforcement learning (MARL) has shown its success across diverse domains, extending its application to large-scale real-world systems still faces significant challenges. Primarily, the high complexity of real-world environments exacerbates the credit assignment problem, substantially reducing training efficiency. Moreover, the variability of agent populations in large-scale scenarios necessitates scalable decision-making mechanisms. To address these challenges, we propose a novel framework: Sequential rollout with Sequential value estimation (SrSv). This framework aims to capture agent interdependence and provide a scalable solution for cooperative MARL. Specifically, SrSv leverages the autoregressive property of the Transformer model to handle varying populations through sequential action rollout. Furthermore, to capture the interdependence of policy distributions and value functions among multiple agents, we introduce an innovative sequential value estimation methodology and integrates the value approximation into an attention-based sequential model. We evaluate SrSv on three benchmarks: Multi-Agent MuJoCo, StarCraft Multi-Agent Challenge, and DubinsCars. Experimental results demonstrate that SrSv significantly outperforms baseline methods in terms of training efficiency without compromising convergence performance. Moreover, when implemented in a large-scale DubinsCar system with 1,024 agents, our framework surpasses existing benchmarks, highlighting the excellent scalability of SrSv.

Xiujian Liang, Jiacheng Liu, Mingyang Sun et al.

Robot manipulation in the real world is fundamentally constrained by the visual sim2real gap, where depth observations collected in simulation fail to reflect the complex noise patterns inherent to real sensors. In this work, inspired by the denoising capability of diffusion models, we invert the conventional perspective and propose a clean-to-noisy paradigm that learns to synthesize noisy depth, thereby bridging the visual sim2real gap through purely simulation-driven robotic learning. Building on this idea, we introduce RealD$^2$iff, a hierarchical coarse-to-fine diffusion framework that decomposes depth noise into global structural distortions and fine-grained local perturbations. To enable progressive learning of these components, we further develop two complementary strategies: Frequency-Guided Supervision (FGS) for global structure modeling and Discrepancy-Guided Optimization (DGO) for localized refinement. To integrate RealD$^2$iff seamlessly into imitation learning, we construct a pipeline that spans six stages. We provide comprehensive empirical and experimental validation demonstrating the effectiveness of this paradigm. RealD$^2$iff enables two key applications: (1) generating real-world-like depth to construct clean-noisy paired datasets without manual sensor data collection. (2) Achieving zero-shot sim2real robot manipulation, substantially improving real-world performance without additional fine-tuning.

Mingyang Sun, Pengxiang Ding, Weinan Zhang et al.

While behavior cloning with flow/diffusion policies excels at learning complex skills from demonstrations, it remains vulnerable to distributional shift, and standard RL methods struggle to fine-tune these models due to their iterative inference process and the limitations of existing workarounds. In this work, we introduce the Stepwise Flow Policy (SWFP) framework, founded on the key insight that discretizing the flow matching inference process via a fixed-step Euler scheme inherently aligns it with the variational Jordan-Kinderlehrer-Otto (JKO) principle from optimal transport. SWFP decomposes the global flow into a sequence of small, incremental transformations between proximate distributions. Each step corresponds to a JKO update, regularizing policy changes to stay near the previous iterate and ensuring stable online adaptation with entropic regularization. This decomposition yields an efficient algorithm that fine-tunes pre-trained flows via a cascade of small flow blocks, offering significant advantages: simpler/faster training of sub-models, reduced computational/memory costs, and provable stability grounded in Wasserstein trust regions. Comprehensive experiments demonstrate SWFP's enhanced stability, efficiency, and superior adaptation performance across diverse robotic control benchmarks.

Mingyang Sun, Jiude Wei, Qichen He et al.

Enabling robots to perform precise and generalized manipulation in unstructured environments remains a fundamental challenge in embodied AI. While Vision-Language Models (VLMs) have demonstrated remarkable capabilities in semantic reasoning and task planning, a significant gap persists between their high-level understanding and the precise physical execution required for real-world manipulation. To bridge this "semantic-to-physical" gap, we introduce GRACE, a novel framework that grounds VLM-based reasoning through executable analytic concepts (EAC)-mathematically defined blueprints that encode object affordances, geometric constraints, and semantics of manipulation. Our approach integrates a structured policy scaffolding pipeline that turn natural language instructions and visual information into an instantiated EAC, from which we derive grasp poses, force directions and plan physically feasible motion trajectory for robot execution. GRACE thus provides a unified and interpretable interface between high-level instruction understanding and low-level robot control, effectively enabling precise and generalizable manipulation through semantic-physical grounding. Extensive experiments demonstrate that GRACE achieves strong zero-shot generalization across a variety of articulated objects in both simulated and real-world environments, without requiring task-specific training.

Yilin Li, Guozhu Meng, Mingyang Sun et al.

On-device deep learning models have extensive real world demands. Deep learning compilers efficiently compile models into executables for deployment on edge devices, but these executables may face the threat of reverse engineering. Previous studies have attempted to decompile DNN executables, but they face challenges in handling compilation optimizations and analyzing quantized compiled models. In this paper, we present NeuroDeX to unlock diverse support in decompiling DNN executables. NeuroDeX leverages the semantic understanding capabilities of LLMs along with dynamic analysis to accurately and efficiently perform operator type recognition, operator attribute recovery and model reconstruction. NeuroDeX can recover DNN executables into high-level models towards compilation optimizations, different architectures and quantized compiled models. We conduct experiments on 96 DNN executables across 12 common DNN models. Extensive experimental results demonstrate that NeuroDeX can decompile non-quantized executables into nearly identical high-level models. NeuroDeX can recover functionally similar high-level models for quantized executables, achieving an average top-1 accuracy of 72%. NeuroDeX offers a more comprehensive and effective solution compared to previous DNN executables decompilers.

Jian Huang, Yongli Zhu, Linna Xu et al.

In this paper, an edge-side model training study is conducted on a resource-limited smart meter. The motivation of grid-edge intelligence and the concept of on-device training are introduced. Then, the technical preparation steps for on-device training are described. A case study on the task of photovoltaic power forecasting is presented, where two representative machine learning models are investigated: a gradient boosting tree model and a recurrent neural network model. To adapt to the resource-limited situation in the smart meter, "mixed"- and "reduced"-precision training schemes are also devised. Experiment results demonstrate the feasibility of economically achieving grid-edge intelligence via the existing advanced metering infrastructures.

Zeyu Xiao, Zhenyi Wu, Mingyang Sun et al.

3D Gaussian Splatting has achieved remarkable success in reconstructing both static and dynamic 3D scenes. However, in a scene represented by 3D Gaussian primitives, interactions between objects suffer from inaccurate 3D segmentation, imprecise deformation among different materials, and severe rendering artifacts. To address these challenges, we introduce PIG: Physically-Based Multi-Material Interaction with 3D Gaussians, a novel approach that combines 3D object segmentation with the simulation of interacting objects in high precision. Firstly, our method facilitates fast and accurate mapping from 2D pixels to 3D Gaussians, enabling precise 3D object-level segmentation. Secondly, we assign unique physical properties to correspondingly segmented objects within the scene for multi-material coupled interactions. Finally, we have successfully embedded constraint scales into deformation gradients, specifically clamping the scaling and rotation properties of the Gaussian primitives to eliminate artifacts and achieve geometric fidelity and visual consistency. Experimental results demonstrate that our method not only outperforms the state-of-the-art (SOTA) in terms of visual quality, but also opens up new directions and pipelines for the field of physically realistic scene generation.

Qipeng Yan, Mingyang Sun, Lihua Zhang

Real-time rendering of high-fidelity and animatable avatars from monocular videos remains a challenging problem in computer vision and graphics. Over the past few years, the Neural Radiance Field (NeRF) has made significant progress in rendering quality but behaves poorly in run-time performance due to the low efficiency of volumetric rendering. Recently, methods based on 3D Gaussian Splatting (3DGS) have shown great potential in fast training and real-time rendering. However, they still suffer from artifacts caused by inaccurate geometry. To address these problems, we propose 2DGS-Avatar, a novel approach based on 2D Gaussian Splatting (2DGS) for modeling animatable clothed avatars with high-fidelity and fast training performance. Given monocular RGB videos as input, our method generates an avatar that can be driven by poses and rendered in real-time. Compared to 3DGS-based methods, our 2DGS-Avatar retains the advantages of fast training and rendering while also capturing detailed, dynamic, and photo-realistic appearances. We conduct abundant experiments on popular datasets such as AvatarRex and THuman4.0, demonstrating impressive performance in both qualitative and quantitative metrics.

Liyu Zhang, Haochi Wu, Xu Wan et al.

Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action sample, thus eliminating the need for retraining on offline data. The frozen offline critic is incorporated with the online target critic weighted by a state-action-adaptive coefficient. This coefficient aims to capture the offline degree of samples at the state-action level, and is updated adaptively during training. In practice, SAMG could be easily integrated with Q-function-based algorithms. Theoretical analysis shows good optimality and lower estimation error. Empirically, SAMG outperforms state-of-the-art O2O RL algorithms on the D4RL benchmark.

Zhenguo Zhang, Qianqian Yang, Shibo He et al.

Semantic-oriented communication has been considered as a promising to boost the bandwidth efficiency by only transmitting the semantics of the data. In this paper, we propose a multi-level semantic aware communication system for wireless image transmission, named MLSC-image, which is based on the deep learning techniques and trained in an end to end manner. In particular, the proposed model includes a multilevel semantic feature extractor, that extracts both the highlevel semantic information, such as the text semantics and the segmentation semantics, and the low-level semantic information, such as local spatial details of the images. We employ a pretrained image caption to capture the text semantics and a pretrained image segmentation model to obtain the segmentation semantics. These high-level and low-level semantic features are then combined and encoded by a joint semantic and channel encoder into symbols to transmit over the physical channel. The numerical results validate the effectiveness and efficiency of the proposed semantic communication system, especially under the limited bandwidth condition, which indicates the advantages of the high-level semantics in the compression of images.

Cheng Cheng, Guijun Ma, Yong Zhang et al.

In industrial applications, nearly half the failures of motors are caused by the degradation of rolling element bearings (REBs). Therefore, accurately estimating the remaining useful life (RUL) for REBs are of crucial importance to ensure the reliability and safety of mechanical systems. To tackle this challenge, model-based approaches are often limited by the complexity of mathematical modeling. Conventional data-driven approaches, on the other hand, require massive efforts to extract the degradation features and construct health index. In this paper, a novel online data-driven framework is proposed to exploit the adoption of deep convolutional neural networks (CNN) in predicting the RUL of bearings. More concretely, the raw vibrations of training bearings are first processed using the Hilbert-Huang transform (HHT) and a novel nonlinear degradation indicator is constructed as the label for learning. The CNN is then employed to identify the hidden pattern between the extracted degradation indicator and the vibration of training bearings, which makes it possible to estimate the degradation of the test bearings automatically. Finally, testing bearings' RULs are predicted by using a $ε$-support vector regression model. The superior performance of the proposed RUL estimation framework, compared with the state-of-the-art approaches, is demonstrated through the experimental results. The generality of the proposed CNN model is also validated by transferring to bearings undergoing different operating conditions.