Keze Wang

Hefeng Wu, Yandong Chen, Lingbo Liu et al.

The class-agnostic counting (CAC) task has recently been proposed to solve the problem of counting all objects of an arbitrary class with several exemplars given in the input image. To address this challenging task, existing leading methods all resort to density map regression, which renders them impractical for downstream tasks that require object locations and restricts their ability to well explore the scale information of exemplars for supervision. To address the limitations, we propose a novel localization-based CAC approach, termed Scale-modulated Query and Localization Network (SQLNet). It fully explores the scales of exemplars in both the query and localization stages and achieves effective counting by accurately locating each object and predicting its approximate size. Specifically, during the query stage, rich discriminative representations of the target class are acquired by the Hierarchical Exemplars Collaborative Enhancement (HECE) module from the few exemplars through multi-scale exemplar cooperation with equifrequent size prompt embedding. These representations are then fed into the Exemplars-Unified Query Correlation (EUQC) module to interact with the query features in a unified manner and produce the correlated query tensor. In the localization stage, the Scale-aware Multi-head Localization (SAML) module utilizes the query tensor to predict the confidence, location, and size of each potential object. Moreover, a scale-aware localization loss is introduced, which exploits flexible location associations and exemplar scales for supervision to optimize the model performance. Extensive experiments demonstrate that SQLNet outperforms state-of-the-art methods on popular CAC benchmarks, achieving excellent performance not only in counting accuracy but also in localization and bounding box generation. Our codes will be available at https://github.com/HCPLab-SYSU/SQLNet

Zheng Chen, Kai Liu, Jingkai Wang et al.

This paper presents the NTIRE 2026 image super-resolution ($\times$4) challenge, one of the associated competitions of the NTIRE 2026 Workshop at CVPR 2026. The challenge aims to reconstruct high-resolution (HR) images from low-resolution (LR) inputs generated through bicubic downsampling with a $\times$4 scaling factor. The objective is to develop effective super-resolution solutions and analyze recent advances in the field. To reflect the evolving objectives of image super-resolution, the challenge includes two tracks: (1) a restoration track, which emphasizes pixel-wise fidelity and ranks submissions based on PSNR; and (2) a perceptual track, which focuses on visual realism and evaluates results using a perceptual score. A total of 194 participants registered for the challenge, with 31 teams submitting valid entries. This report summarizes the challenge design, datasets, evaluation protocol, main results, and methods of participating teams. The challenge provides a unified benchmark and offers insights into current progress and future directions in image super-resolution.

Jesen Zhang, Ningyuan Liu, Kaitong Cai et al.

Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approaches supervise only the final answer while ignoring the reliability of the intermediate reasoning process. We introduce SR-MCR, a lightweight and label-free framework that aligns reasoning by exploiting intrinsic process signals derived directly from model outputs. Five self-referential cues -- semantic alignment, lexical fidelity, non-redundancy, visual grounding, and step consistency -- are integrated into a normalized, reliability-weighted reward that provides fine-grained process-level guidance. A critic-free GRPO objective, enhanced with a confidence-aware cooling mechanism, further stabilizes training and suppresses trivial or overly confident generations. Built on Qwen2.5-VL, SR-MCR improves both answer accuracy and reasoning coherence across a broad set of visual benchmarks; among open-source models of comparable size, SR-MCR-7B achieves state-of-the-art performance with an average accuracy of 81.4%. Ablation studies confirm the independent contributions of each reward term and the cooling module.

Zimeng Huang, Jinxin Ke, Xiaoxuan Fan et al.

Large Vision-Language Models (LVLMs) have exhibited remarkable progress. However, deficiencies remain compared to human intelligence, such as hallucination and shallow pattern matching. In this work, we aim to evaluate a fundamental yet underexplored intelligence: association, a cornerstone of human cognition for creative thinking and knowledge integration. Current benchmarks, often limited to closed-ended tasks, fail to capture the complexity of open-ended association reasoning vital for real-world applications. To address this, we present MM-OPERA, a systematic benchmark with 11,497 instances across two open-ended tasks: Remote-Item Association (RIA) and In-Context Association (ICA), aligning association intelligence evaluation with human psychometric principles. It challenges LVLMs to resemble the spirit of divergent thinking and convergent associative reasoning through free-form responses and explicit reasoning paths. We deploy tailored LLM-as-a-Judge strategies to evaluate open-ended outputs, applying process-reward-informed judgment to dissect reasoning with precision. Extensive empirical studies on state-of-the-art LVLMs, including sensitivity analysis of task instances, validity analysis of LLM-as-a-Judge strategies, and diversity analysis across abilities, domains, languages, cultures, etc., provide a comprehensive and nuanced understanding of the limitations of current LVLMs in associative reasoning, paving the way for more human-like and general-purpose AI. The dataset and code are available at https://github.com/MM-OPERA-Bench/MM-OPERA.

Zeqing Wang, Keze Wang, Lei Zhang

Driven by the growing capacity and training scale, Text-to-Video (T2V) generation models have recently achieved substantial progress in video quality, length, and instruction-following capability. However, whether these models can understand physics and generate physically plausible videos remains a question. While Vision-Language Models (VLMs) have been widely used as general-purpose evaluators in various applications, they struggle to identify the physically impossible content from generated videos. To investigate this issue, we construct a \textbf{PID} (\textbf{P}hysical \textbf{I}mplausibility \textbf{D}etection) dataset, which consists of a \textit{test split} of 500 manually annotated videos and a \textit{train split} of 2,588 paired videos, where each implausible video is generated by carefully rewriting the caption of its corresponding real-world video to induce T2V models producing physically implausible content. With the constructed dataset, we introduce a lightweight fine-tuning approach, enabling VLMs to not only detect physically implausible events but also generate textual explanations on the violated physical principles. Taking the fine-tuned VLM as a physical plausibility detector and explainer, namely \textbf{PhyDetEx}, we benchmark a series of state-of-the-art T2V models to assess their adherence to physical laws. Our findings show that although recent T2V models have made notable progress toward generating physically plausible content, understanding and adhering to physical laws remains a challenging issue, especially for open-source models. Our dataset, training code, and checkpoints are available at \href{https://github.com/Zeqing-Wang/PhyDetEx}{https://github.com/Zeqing-Wang/PhyDetEx}.

Hefeng Wu, Hao Jiang, Keze Wang et al.

While deep neural networks have achieved remarkable performance, they tend to lack transparency in prediction. The pursuit of greater interpretability in neural networks often results in a degradation of their original performance. Some works strive to improve both interpretability and performance, but they primarily depend on meticulously imposed conditions. In this paper, we propose a simple yet effective framework that acquires more explainable activation heatmaps and simultaneously increase the model performance, without the need for any extra supervision. Specifically, our concise framework introduces a new metric, i.e., explanation consistency, to reweight the training samples adaptively in model learning. The explanation consistency metric is utilized to measure the similarity between the model's visual explanations of the original samples and those of semantic-preserved adversarial samples, whose background regions are perturbed by using image adversarial attack techniques. Our framework then promotes the model learning by paying closer attention to those training samples with a high difference in explanations (i.e., low explanation consistency), for which the current model cannot provide robust interpretations. Comprehensive experimental results on various benchmarks demonstrate the superiority of our framework in multiple aspects, including higher recognition accuracy, greater data debiasing capability, stronger network robustness, and more precise localization ability on both regular networks and interpretable networks. We also provide extensive ablation studies and qualitative analyses to unveil the detailed contribution of each component.

Wentao Wan, Nan Kang, Zeqing Wang et al.

Recently, Visual Programming (VProg) has emerged as a significant framework for visual reasoning (VR) tasks due to its interpretability and cross-task generality. However, even with invoking powerful pre-trained Vision-Language models (VLMs) as visual sub-modules, the performance of VProg on specific VR tasks is markedly inferior compared to well-trained task-specific networks. Although invoking task-specific models can further enhance the performance of VProg on specific VR tasks, it greatly diminishes the cross-task generalization ability of VProg. Besides, the non-differentiable nature of VProg prevents direct fine-tuning on specific VR tasks for further performance improvement. Attempt to address these issues, we propose SDVP, a Stepwise Distillation learning strategy for non-differentiable VPorg across various VR tasks. Specifically, our SDVP stepwise distills the capabilities of existing, well-trained small task-specific models for decomposed visual sub-tasks in VProg into the much larger VLMs invoked by corresponding visual sub-modules. Besides, distilling the knowledge of little-size task-specific models into pre-trained larger VLMs rather than replacing them helps keep the cross-task abilities of VProgs. Extensive and comprehensive experimental results on different VProg frameworks demonstrate that our SDVP obtains significant performance gains on specific VR benchmarks, i.e., GQA (+2.4\%) and NLVRv2 (+6.2\%) for VisProg and GQA (+6.5\%) and NLVRv2 (+4.0\%) for ViperGPT, and also maintains a promising performance for VProg on unseen and previous VR tasks.

Jusheng Zhang, Kaitong Cai, Xiaoyang Guo et al.

The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critical question remains: is such reasoning genuinely grounded in visual evidence and logically coherent? Existing benchmarks emphasize generation but neglect verification, i.e., the capacity to assess whether a reasoning chain is both visually consistent and logically valid. To fill this gap, we introduce MM-CoT, a diagnostic benchmark specifically designed to probe the visual grounding and logical coherence of CoT reasoning in MMs. Instead of generating free-form explanations, models must select the sole event chain that satisfies two orthogonal constraints: (i) visual consistency, ensuring all steps are anchored in observable evidence, and (ii) logical coherence, ensuring causal and commonsense validity. Adversarial distractors are engineered to violate one of these constraints, exposing distinct reasoning failures. We evaluate leading vision-language models on MM-CoT and find that even the most advanced systems struggle, revealing a sharp discrepancy between generative fluency and true reasoning fidelity. MM-CoT shows low correlation with existing benchmarks, confirming that it measures a unique combination of visual grounding and logical reasoning. This benchmark provides a foundation for developing future models that reason not just plausibly, but faithfully and coherently within the visual world.

Jensen Zhang, Ningyuan Liu, Yijia Fan et al.

Large language models (LLMs) often generate hallucinated content that lacks factual or contextual grounding, limiting their reliability in critical applications. Existing approaches such as supervised fine-tuning and reinforcement learning from human feedback are data intensive and computationally expensive, while static parameter editing methods struggle with context dependent errors and catastrophic forgetting. We propose LLM-CAS, a framework that formulates real-time hallucination correction as a hierarchical reinforcement learning problem. LLM-CAS trains an agent to learn a policy that dynamically selects temporary neuron perturbations during inference based on the current context. Unlike prior dynamic approaches that rely on heuristic or predefined adjustments, this policy driven mechanism enables adaptive and fine grained correction without permanent parameter modification. Experiments across multiple language models demonstrate that LLM-CAS consistently improves factual accuracy, achieving gains of 10.98 percentage points on StoryCloze, 2.71 points on TriviaQA, and 2.06 points on the MC1 score of TruthfulQA. These results outperform both static editing methods such as ITI and CAA and the dynamic SADI framework. Overall, LLM-CAS provides an efficient and context aware solution for improving the reliability of LLMs, with promising potential for future multimodal extensions.

Jusheng Zhang, Xiaoyang Guo, Kaitong Cai et al.

Vision-language models (VLMs) have transformed multimodal reasoning, but feeding hundreds of visual patch tokens into LLMs incurs quadratic computational costs, straining memory and context windows. Traditional approaches face a trade-off: continuous compression dilutes high-level semantics such as object identities, while discrete quantization loses fine-grained details such as textures. We introduce HTC-VLM, a hybrid framework that disentangles semantics and appearance through dual channels, i.e., a continuous pathway for fine-grained details via ViT patches and a discrete pathway for symbolic anchors using MGVQ quantization projected to four tokens. These are fused into a 580-token hybrid sequence and compressed into a single voco token via a disentanglement attention mask and bottleneck, ensuring efficient and grounded representations. HTC-VLM achieves an average performance retention of 87.2 percent across seven benchmarks (GQA, VQAv2, MMBench, MME, POPE, SEED-Bench, ScienceQA-Image), outperforming the leading continuous baseline at 81.0 percent with a 580-to-1 compression ratio. Attention analyses show that the compressed token prioritizes the discrete anchor, validating its semantic guidance. Our work demonstrates that a minimalist hybrid design can resolve the efficiency-fidelity dilemma and advance scalable VLMs.

Xingyu Zhou, Leheng Zhang, Xiaorui Zhao et al.

Recently, Vision Transformer has achieved great success in recovering missing details in low-resolution sequences, i.e., the video super-resolution (VSR) task. Despite its superiority in VSR accuracy, the heavy computational burden as well as the large memory footprint hinder the deployment of Transformer-based VSR models on constrained devices. In this paper, we address the above issue by proposing a novel feature-level masked processing framework: VSR with Masked Intra and inter frame Attention (MIA-VSR). The core of MIA-VSR is leveraging feature-level temporal continuity between adjacent frames to reduce redundant computations and make more rational use of previously enhanced SR features. Concretely, we propose an intra-frame and inter-frame attention block which takes the respective roles of past features and input features into consideration and only exploits previously enhanced features to provide supplementary information. In addition, an adaptive block-wise mask prediction module is developed to skip unimportant computations according to feature similarity between adjacent frames. We conduct detailed ablation studies to validate our contributions and compare the proposed method with recent state-of-the-art VSR approaches. The experimental results demonstrate that MIA-VSR improves the memory and computation efficiency over state-of-the-art methods, without trading off PSNR accuracy. The code is available at https://github.com/LabShuHangGU/MIA-VSR.

Wentao Wan, Kaiyu Wu, Qingyang Ma et al.

Recently, Visual Programming (VP) based on large language models (LLMs) has rapidly developed and demonstrated significant potential in complex Visual Reasoning (VR) tasks. Previous works to enhance VP have primarily focused on improving the quality of LLM-generated visual programs. However, they have neglected to optimize the VP-invoked pre-trained models, which serve as modules for the visual sub-tasks decomposed from the targeted tasks by VP. The difficulty is that there are only final labels of targeted VR tasks rather than labels of sub-tasks. Besides, the non-differentiable nature of VP impedes the direct use of efficient gradient-based optimization methods to leverage final labels for end-to-end learning of the entire VP framework. To overcome these issues, we propose EVPG, a method to Enhance Visual Programming for visual reasoning via Probabilistic Graphs. Specifically, we creatively build a directed probabilistic graph according to the variable dependency relationships during the VP executing process, which reconstructs the non-differentiable VP executing process into a differentiable exact probability inference process on this directed probabilistic graph. As a result, this enables the VP framework to utilize the final labels for efficient, gradient-based optimization in end-to-end supervised learning on targeted VR tasks. Extensive and comprehensive experiments demonstrate the effectiveness and advantages of our EVPG, showing significant performance improvements for VP on three classical complex VR tasks: GQA, NLVRv2, and Open Images.

Haijing Liu, Zhiyuan Song, Hefeng Wu et al.

Egocentric Referring Video Object Segmentation (Ego-RVOS) aims to segment the specific object actively involved in a human action, as described by a language query, within first-person videos. This task is critical for understanding egocentric human behavior. However, achieving such segmentation robustly is challenging due to ambiguities inherent in egocentric videos and biases present in training data. Consequently, existing methods often struggle, learning spurious correlations from skewed object-action pairings in datasets and fundamental visual confounding factors of the egocentric perspective, such as rapid motion and frequent occlusions. To address these limitations, we introduce Causal Ego-REferring Segmentation (CERES), a plug-in causal framework that adapts strong, pre-trained RVOS backbones to the egocentric domain. CERES implements dual-modal causal intervention: applying backdoor adjustment principles to counteract language representation biases learned from dataset statistics, and leveraging front-door adjustment concepts to address visual confounding by intelligently integrating semantic visual features with geometric depth information guided by causal principles, creating representations more robust to egocentric distortions. Extensive experiments demonstrate that CERES achieves state-of-the-art performance on Ego-RVOS benchmarks, highlighting the potential of applying causal reasoning to build more reliable models for broader egocentric video understanding.

Kaitong Cai, Jusheng Zhang, Jing Yang et al.

Large vision-language models (VLMs) typically process hundreds or thousands of visual tokens per image or video frame, incurring quadratic attention cost and substantial redundancy. Existing token reduction methods often ignore the textual query or rely on deep attention maps, whose instability under aggressive pruning leads to degraded semantic alignment. We propose FlashVLM, a text guided visual token selection framework that dynamically adapts visual inputs to the query. Instead of relying on noisy attention weights, FlashVLM computes an explicit cross modal similarity between projected image tokens and normalized text embeddings in the language model space. This extrinsic relevance is fused with intrinsic visual saliency using log domain weighting and temperature controlled sharpening. In addition, a diversity preserving partition retains a minimal yet representative set of background tokens to maintain global context. Under identical token budgets and evaluation protocols, FlashVLM achieves beyond lossless compression, slightly surpassing the unpruned baseline while pruning up to 77.8 percent of visual tokens on LLaVA 1.5, and maintaining 92.8 percent accuracy even under 94.4 percent compression. Extensive experiments on 14 image and video benchmarks demonstrate that FlashVLM delivers state of the art efficiency performance trade offs while maintaining strong robustness and generalization across mainstream VLMs.

Jusheng Zhang, Yijia Fan, Kaitong Cai et al.

Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry often spirals costs. Existing paradigms, such as Mixture-of-Agents and knowledge-based routers, rely on heuristic proxies that ignore costs and collapse uncertainty structure, leading to provably suboptimal coordination. We introduce Agora, a framework that reframes coordination as a decentralized market for uncertainty. Agora formalizes epistemic uncertainty into a structured, tradable asset (perceptual, semantic, inferential), and enforces profitability-driven trading among agents based on rational economic rules. A market-aware broker, extending Thompson Sampling, initiates collaboration and guides the system toward cost-efficient equilibria. Experiments on five multimodal benchmarks (MMMU, MMBench, MathVision, InfoVQA, CC-OCR) show that Agora outperforms strong VLMs and heuristic multi-agent strategies, e.g., achieving +8.5% accuracy over the best baseline on MMMU while reducing cost by over 3x. These results establish market-based coordination as a principled and scalable paradigm for building economically viable multi-agent visual intelligence systems.

Kaiyu Wu, Pucheng Han, Hualong Zhang et al.

While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream Reinforcement Fine-Tuning (RFT) can induce Self-Contradictory Reasoning (Self-Contra), where the model's reasoning contradicts its final answer, which is unacceptable in such a high-stakes domain. To address these challenges, we construct WeatherQA, a novel multimodal reasoning benchmark in meteorology. We also propose Logically Consistent Reinforcement Fine-Tuning (LoCo-RFT), which resolves Self-Contra by introducing a logical consistency reward. Furthermore, we introduce Weather-R1, the first reasoning VLM with logical faithfulness in meteorology, to the best of our knowledge. Experiments demonstrate that Weather-R1 improves performance on WeatherQA by 9.8 percentage points over the baseline, outperforming Supervised Fine-Tuning and RFT, and even surpassing the original Qwen2.5-VL-32B. These results highlight the effectiveness of our LoCo-RFT and the superiority of Weather-R1. Our benchmark and code are available at https://github.com/Marcowky/Weather-R1.

Ziyi Tang, Ruilin Wang, Weixing Chen et al.

Despite the progress of foundation models, knowledge-based reasoning remains a persistent challenge due to their limited capacity for knowledge recall and inference. Existing methods primarily focus on encouraging these models to plan and solve problems or extensively sample reasoning chains independently. However, these methods often overlook conceptual errors and inferential fallacies, inevitably leading to a series of notorious issues such as misleading conclusions, cognitive biases, and reduced decision quality. While explicit modeling of causality is argued to hold promise in addressing these issues, contemporary research efforts have thus far fallen short in achieving causality-based foundation models. Drawing inspiration from the orchestration of diverse specialized agents collaborating to tackle intricate tasks, we propose a framework named Causal-Consistency Chain-of-Thought (CaCo-CoT) that harnesses multi-agent collaboration to bolster the faithfulness and causality of foundation models, involving a set of reasoners and evaluators. These agents collaboratively work within a reasoning-and-consensus paradigm to improve faithfulness. The reasoners are tasked with generating reasoning chains for knowledge-intensive problems by mimicking human causal reasoning. Meanwhile, the evaluator scrutinizes the causal consistency of a reasoner's reasoning chain from a non-causal and a counterfactual perspective. Our framework demonstrates significant superiority over state-of-the-art methods through extensive and comprehensive evaluations across text-based and multi-modal knowledge reasoning tasks (e.g., science question answering and commonsense reasoning).

Yue Chen, Yihao Wang, Ziyi Tang et al.

Document Layout Analysis (DLA) pipelines provide structured page representations for retrieval-augmented generation, long-document question answering, and other document intelligence systems, yet their robustness evaluation remains largely area-centric. We identify this Footprint Bias and propose a lightweight output-level auditing framework that decouples probe construction, policy-driven targeting, and structure-aware diagnosis. The framework combines Block-level Structural Loss Rate (B-SLR), granularity-aware exposure descriptors, and pathway attribution to analyze where perturbations interact with layout structure and how failures propagate. Across MinerU and PP-StructureV3 on 1,000 pages, affected area weakly tracks perturbation-induced OCR instability (R^2=0.384/0.110), whereas B-SLR aligns much more closely with it (R^2=0.727/0.916). Exposure descriptors further separate occlusion- and topology-dominant pathways, and small structurally targeted probes cause downstream QA/retrieval degradation comparable to larger-footprint perturbations. These results shift DLA robustness evaluation from footprint-based stress testing toward structure-aware vulnerability auditing.

Zhixing Zhang, Jesen Zhang, Hao Liu et al.

Foundation models for agriculture are increasingly trained on massive spatiotemporal data (e.g., multi-spectral remote sensing, soil grids, and field-level management logs) and achieve strong performance on forecasting and monitoring. However, these models lack language-based reasoning and interactive capabilities, limiting their usefulness in real-world agronomic workflows. Meanwhile, large language models (LLMs) excel at interpreting and generating text, but cannot directly reason over high-dimensional, heterogeneous agricultural datasets. We bridge this gap with an agentic framework for agricultural science. It provides a Python execution environment, AgriWorld, exposing unified tools for geospatial queries over field parcels, remote-sensing time-series analytics, crop growth simulation, and task-specific predictors (e.g., yield, stress, and disease risk). On top of this environment, we design a multi-turn LLM agent, Agro-Reflective, that iteratively writes code, observes execution results, and refines its analysis via an execute-observe-refine loop. We introduce AgroBench, with scalable data generation for diverse agricultural QA spanning lookups, forecasting, anomaly detection, and counterfactual "what-if" analysis. Experiments outperform text-only and direct tool-use baselines, validating execution-driven reflection for reliable agricultural reasoning.

Yihao Wang, Jusheng Zhang, Ziyi Tang et al.

Referring Expression Segmentation (RES) is a core vision-language segmentation task that enables pixel-level understanding of targets via free-form linguistic expressions, supporting critical applications such as human-robot interaction and augmented reality. Despite the progress of Multimodal Large Language Model (MLLM)-based approaches, existing RES methods still suffer from two key limitations: first, the coarse bounding boxes from MLLMs lead to redundant or non-discriminative point prompts; second, the prevalent reliance on textual coordinate reasoning is unreliable, as it fails to distinguish targets from visually similar distractors. To address these issues, we propose \textbf{\model}, a novel RES framework integrating \textbf{E}ntropy-\textbf{B}ased Point \textbf{D}iscovery (\textbf{EBD}) and \textbf{V}ision-\textbf{B}ased \textbf{R}easoning (\textbf{VBR}). Specifically, EBD identifies high-information candidate points by modeling spatial uncertainty within coarse bounding boxes, treating point selection as an information maximization process. VBR verifies point correctness through joint visual-semantic alignment, abandoning text-only coordinate inference for more robust validation. Built on these components, \model implements a coarse-to-fine workflow: bounding box initialization, entropy-guided point discovery, vision-based validation, and mask decoding. Extensive evaluations on four benchmark datasets (RefCOCO, RefCOCO+, RefCOCOg, and ReasonSeg) demonstrate that \model achieves new state-of-the-art performance across all four benchmarks, highlighting its effectiveness in generating accurate and semantically grounded segmentation masks with minimal prompts.

Yijia Fan, Jusheng Zhang, Kaitong Cai et al.

Multi-label classification (MLC) remains vulnerable to label imbalance, spurious correlations, and distribution shifts, challenges that are particularly detrimental to rare label prediction. To address these limitations, we introduce the Causal Cooperative Game (CCG) framework, which conceptualizes MLC as a cooperative multi-player interaction. CCG unifies explicit causal discovery via Neural Structural Equation Models with a counterfactual curiosity reward to drive robust feature learning. Furthermore, it incorporates a causal invariance loss to ensure generalization across diverse environments, complemented by a specialized enhancement strategy for rare labels. Extensive benchmarking demonstrates that CCG substantially outperforms strong baselines in both rare label prediction and overall robustness. Through rigorous ablation studies and qualitative analysis, we validate the efficacy and interpretability of our components, underscoring the potential of synergizing causal inference with cooperative game theory for advancing multi-label learning.

Qinglin Zeng, Kaitong Cai, Ruiqi Chen et al.

Maintaining narrative coherence and visual consistency remains a central challenge in open-domain video generation. Existing text-to-video models often treat each shot independently, resulting in identity drift, scene inconsistency, and unstable temporal structure. We propose CoAgent, a collaborative and closed-loop framework for coherent video generation that formulates the process as a plan-synthesize-verify pipeline. Given a user prompt, style reference, and pacing constraints, a Storyboard Planner decomposes the input into structured shot-level plans with explicit entities, spatial relations, and temporal cues. A Global Context Manager maintains entity-level memory to preserve appearance and identity consistency across shots. Each shot is then generated by a Synthesis Module under the guidance of a Visual Consistency Controller, while a Verifier Agent evaluates intermediate results using vision-language reasoning and triggers selective regeneration when inconsistencies are detected. Finally, a pacing-aware editor refines temporal rhythm and transitions to match the desired narrative flow. Extensive experiments demonstrate that CoAgent significantly improves coherence, visual consistency, and narrative quality in long-form video generation.

Ruiqi Chen, Kaitong Cai, Yijia Fan et al.

Traditional animation production involves complex pipelines and significant manual labor cost. While recent video generation models such as Sora, Kling, and CogVideoX achieve impressive results on natural video synthesis, they exhibit notable limitations when applied to animation generation. Recent efforts, such as AniSora, demonstrate promising performance by fine-tuning image-to-video models for animation styles, yet analogous exploration in the text-to-video setting remains limited. In this work, we present PTTA, a pure text-to-animation framework for high-quality animation creation. We first construct a small-scale but high-quality paired dataset of animation videos and textual descriptions. Building upon the pretrained text-to-video model HunyuanVideo, we perform fine-tuning to adapt it to animation-style generation. Extensive visual evaluations across multiple dimensions show that the proposed approach consistently outperforms comparable baselines in animation video synthesis.

Qinglin Zeng, Jing Yang, Keze Wang

Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on multiple reasoning trajectories, often incur substantial computational overhead. To improve efficiency, prior work has leveraged internal confidence signals, where early stopping strategies such as DeepConf reduce cost by terminating low-confidence trajectories. However, this strategy discards incomplete reasoning paths and wastes partial computation. We propose reflective confidence, a novel reasoning framework that transforms low-confidence signals from termination indicators into reflection triggers. When confidence falls below a threshold, instead of stopping generation, the model produces a reflection prompt to analyze the current reasoning state, identify potential errors, and continue generation along a corrected trajectory. Experiments on mathematical reasoning benchmarks, including AIME 2025, demonstrate significant accuracy improvements over advanced early-stopping baselines at comparable computational cost, validating the effectiveness of proactive self-correction over passive discarding.

Ningyuan Liu, Jing Yang, Kaitong Cai et al.

Full parameter fine tuning is a key technique for adapting large language models (LLMs) to downstream tasks, but it incurs substantial memory overhead due to the need to cache extensive intermediate activations for backpropagation. This bottleneck makes full fine tuning of contemporary large scale LLMs challenging in practice. Existing distributed training frameworks such as DeepSpeed alleviate this issue using techniques like ZeRO and FSDP, which rely on multi GPU memory or CPU offloading, but often require additional hardware resources and reduce training speed. We introduce RevFFN, a memory efficient fine tuning paradigm for mixture of experts (MoE) LLMs. RevFFN employs carefully designed reversible Transformer blocks that allow reconstruction of layer input activations from outputs during backpropagation, eliminating the need to store most intermediate activations in memory. While preserving the expressive capacity of MoE architectures, this approach significantly reduces peak memory consumption for full parameter fine tuning. As a result, RevFFN enables efficient full fine tuning on a single consumer grade or server grade GPU.

Kaitong Cai, Jensen Zhang, Jing Yang et al.

We introduce SirenPose, a geometry-aware loss formulation that integrates the periodic activation properties of sinusoidal representation networks with keypoint-based geometric supervision, enabling accurate and temporally consistent reconstruction of dynamic 3D scenes from monocular videos. Existing approaches often struggle with motion fidelity and spatiotemporal coherence in challenging settings involving fast motion, multi-object interaction, occlusion, and rapid scene changes. SirenPose incorporates physics inspired constraints to enforce coherent keypoint predictions across both spatial and temporal dimensions, while leveraging high frequency signal modeling to capture fine grained geometric details. We further expand the UniKPT dataset to 600,000 annotated instances and integrate graph neural networks to model keypoint relationships and structural correlations. Extensive experiments on benchmarks including Sintel, Bonn, and DAVIS demonstrate that SirenPose consistently outperforms state-of-the-art methods. On DAVIS, SirenPose achieves a 17.8 percent reduction in FVD, a 28.7 percent reduction in FID, and a 6.0 percent improvement in LPIPS compared to MoSCA. It also improves temporal consistency, geometric accuracy, user score, and motion smoothness. In pose estimation, SirenPose outperforms Monst3R with lower absolute trajectory error as well as reduced translational and rotational relative pose error, highlighting its effectiveness in handling rapid motion, complex dynamics, and physically plausible reconstruction.

Zeqing Wang, Wentao Wan, Qiqing Lao et al.

Recently, to comprehensively improve Vision Language Models (VLMs) for Visual Question Answering (VQA), several methods have been proposed to further reinforce the inference capabilities of VLMs to independently tackle VQA tasks rather than some methods that only utilize VLMs as aids to Large Language Models (LLMs). However, these methods ignore the rich common-sense knowledge inside the given VQA image sampled from the real world. Thus, they cannot fully use the powerful VLM for the given VQA question to achieve optimal performance. Attempt to overcome this limitation and inspired by the human top-down reasoning process, i.e., systematically exploring relevant issues to derive a comprehensive answer, this work introduces a novel, explainable multi-agent collaboration framework by leveraging the expansive knowledge of Large Language Models (LLMs) to enhance the capabilities of VLMs themselves. Specifically, our framework comprises three agents, i.e., Responder, Seeker, and Integrator, to collaboratively answer the given VQA question by seeking its relevant issues and generating the final answer in such a top-down reasoning process. The VLM-based Responder agent generates the answer candidates for the question and responds to other relevant issues. The Seeker agent, primarily based on LLM, identifies relevant issues related to the question to inform the Responder agent and constructs a Multi-View Knowledge Base (MVKB) for the given visual scene by leveraging the build-in world knowledge of LLM. The Integrator agent combines knowledge from the Seeker agent and the Responder agent to produce the final VQA answer. Extensive and comprehensive evaluations on diverse VQA datasets with a variety of VLMs demonstrate the superior performance and interpretability of our framework over the baseline method in the zero-shot setting without extra training cost.

Jinzhou Tang, Sidi Liu, Waikit Xiu et al.

A fundamental challenge in embodied AI is verifying if agents build internal models of spatial structure or merely learn to mimic task-specific expert trajectories. This is critical as foundational approaches rooted in action-centric tasks (e.g., VLN) and reasoning-centric tasks (e.g., EQA) often share a common limitation: they lack a learning signal that forces them to encode fine-grained spatial relationships (like topology or distance) over long-range, fragmented experiences. To address this, we first propose LASAR, an architecture featuring a dual-memory system designed to maintain both episodic experiences and a semantic cognitive map. We then introduce Spatio-temporal Contextual Representation Learning (ST-CRL), a contrastive objective designed to train this architecture. ST-CRL leverages spatio-temporal cues from cognitive queries generated through annotated spatio-temporal context in simulation to build sample pairs, thereby forming the internal cognitive map from the agent's experiences. Experiments demonstrate that our method achieves 2\%-3.5\% gains in both zero-shot generalization on standard VLN-CE and VSI-Bench benchmarks. We also demonstrate that our proposed cognitive map has high self-consistency.

Zhihao Zhan, Yuhao Chen, Jiaying Zhou et al.

Vision-Language-Action (VLA) models have demonstrated impressive capabilities in generalized robotic control; however, they remain notoriously brittle to linguistic perturbations. We identify a critical ``modality collapse'' phenomenon where strong visual priors overwhelm sparse linguistic signals, causing agents to overfit to specific instruction phrasings while ignoring the underlying semantic intent. To address this, we propose \textbf{Residual Semantic Steering (RSS)}, a probabilistic framework that disentangles physical affordance from semantic execution. RSS introduces two theoretical innovations: (1) \textbf{Monte Carlo Syntactic Integration}, which approximates the true semantic posterior via dense, LLM-driven distributional expansion, and (2) \textbf{Residual Affordance Steering}, a dual-stream decoding mechanism that explicitly isolates the causal influence of language by subtracting the visual affordance prior. Theoretical analysis suggests that RSS effectively maximizes the mutual information between action and intent while suppressing visual distractors. Empirical results across diverse manipulation benchmarks demonstrate that RSS achieves state-of-the-art robustness, maintaining performance even under adversarial linguistic perturbations.

Jusheng Zhang, Ningyuan Liu, Qinhan Lyu et al.

Deep neural networks typically treat nonlinearities as fixed primitives (e.g., ReLU), limiting both interpretability and the granularity of control over the induced function class. While recent additive models (like KANs) attempt to address this using splines, they often suffer from computational inefficiency and boundary instability. We propose the Rational-ANOVA Network (RAN), a foundational architecture grounded in functional ANOVA decomposition and Padé-style rational approximation. RAN models f(x) as a composition of main effects and sparse pairwise interactions, where each component is parameterized by a stable, learnable rational unit. Crucially, we enforce a strictly positive denominator, which avoids poles and numerical instability while capturing sharp transitions and near-singular behaviors more efficiently than polynomial bases. This ANOVA structure provides an explicit low-order interaction bias for data efficiency and interpretability, while the rational parameterization significantly improves extrapolation. Across controlled function benchmarks and vision classification tasks (e.g., CIFAR-10) under matched parameter and compute budgets, RAN matches or surpasses parameter-matched MLPs and learnable-activation baselines, with better stability and throughput. Code is available at https://github.com/jushengzhang/Rational-ANOVA-Networks.git.

Linsheng Chen, Guangrun Wang, Liuchun Yuan et al.

Neural Radiance Fields (NeRF) have garnered remarkable success in novel view synthesis. Nonetheless, the task of generating high-quality images for novel views persists as a critical challenge. While the existing efforts have exhibited commendable progress, capturing intricate details, enhancing textures, and achieving superior Peak Signal-to-Noise Ratio (PSNR) metrics warrant further focused attention and advancement. In this work, we propose NeRF-VPT, an innovative method for novel view synthesis to address these challenges. Our proposed NeRF-VPT employs a cascading view prompt tuning paradigm, wherein RGB information gained from preceding rendering outcomes serves as instructive visual prompts for subsequent rendering stages, with the aspiration that the prior knowledge embedded in the prompts can facilitate the gradual enhancement of rendered image quality. NeRF-VPT only requires sampling RGB data from previous stage renderings as priors at each training stage, without relying on extra guidance or complex techniques. Thus, our NeRF-VPT is plug-and-play and can be readily integrated into existing methods. By conducting comparative analyses of our NeRF-VPT against several NeRF-based approaches on demanding real-scene benchmarks, such as Realistic Synthetic 360, Real Forward-Facing, Replica dataset, and a user-captured dataset, we substantiate that our NeRF-VPT significantly elevates baseline performance and proficiently generates more high-quality novel view images than all the compared state-of-the-art methods. Furthermore, the cascading learning of NeRF-VPT introduces adaptability to scenarios with sparse inputs, resulting in a significant enhancement of accuracy for sparse-view novel view synthesis. The source code and dataset are available at \url{https://github.com/Freedomcls/NeRF-VPT}.

Yihao Wang, Zijian He, Jie Ren et al.

Retrieval shapes how language models access and ground knowledge in retrieval-augmented generation (RAG). In historical research, the target is often not an arbitrary relevant passage, but the exact record for a specific regnal month, where temporal consistency matters as much as topical relevance. This is especially challenging for Classical Chinese annals, where time is expressed through terse, implicit, non-Gregorian reign phrases that must be interpreted from surrounding context, so semantically plausible evidence can still be temporally invalid. We introduce \textbf{ChunQiuTR}, a time-keyed retrieval benchmark built from the \textit{Spring and Autumn Annals} and its exegetical tradition. ChunQiuTR organizes records by month-level reign keys and includes chrono-near confounders that mirror realistic retrieval failures. We further propose \textbf{CTD} (Calendrical Temporal Dual-encoder), a time-aware dual-encoder that combines Fourier-based absolute calendrical context with relative offset biasing. Experiments show consistent gains over strong semantic dual-encoder baselines under time-keyed evaluation, supporting retrieval-time temporal consistency as a key prerequisite for faithful downstream historical RAG. Our code and datasets are available at \href{https://github.com/xbdxwyh/ChunQiuTR}{\texttt{github.com/xbdxwyh/ChunQiuTR}}.

Zeqing Wang, Xinyu Wei, Bairui Li et al.

The recent rapid advancement of Text-to-Video (T2V) generation technologies, which are critical to build ``world models'', makes the existing benchmarks increasingly insufficient to evaluate state-of-the-art T2V models. First, current evaluation dimensions, such as per-frame aesthetic quality and temporal consistency, are no longer able to differentiate state-of-the-art T2V models. Second, event-level temporal causality, which not only distinguishes video from other modalities but also constitutes a crucial component of world models, is severely underexplored in existing benchmarks. Third, existing benchmarks lack a systematic assessment of world knowledge, which are essential capabilities for building world models. To address these issues, we introduce VideoVerse, a comprehensive benchmark that focuses on evaluating whether a T2V model could understand complex temporal causality and world knowledge in the real world. We collect representative videos across diverse domains (e.g., natural landscapes, sports, indoor scenes, science fiction, chemical and physical experiments) and extract their event-level descriptions with inherent temporal causality, which are then rewritten into text-to-video prompts by independent annotators. For each prompt, we design a suite of binary evaluation questions from the perspective of dynamic and static properties, with a total of ten carefully defined evaluation dimensions. In total, our VideoVerse comprises 300 carefully curated prompts, involving 815 events and 793 binary evaluation questions. Consequently, a human preference aligned QA-based evaluation pipeline is developed by using modern vision-language models. Finally, we perform a systematic evaluation of state-of-the-art open-source and closed-source T2V models on VideoVerse, providing in-depth analysis on how far the current T2V generators are from world models.

Zeqing Wang, Shiyuan Zhang, Chengpei Tang et al.

Reasoning about temporal causality, particularly irreversible transformations of objects governed by real-world knowledge (e.g., fruit decay and human aging), is a fundamental aspect of human visual understanding. Unlike temporal perception based on simple event sequences, this form of reasoning requires a deeper comprehension of how object states change over time. Although the current powerful Vision-Language Models (VLMs) have demonstrated impressive performance on a wide range of downstream tasks, their capacity to reason about temporal causality remains underexplored. To address this gap, we introduce \textbf{TimeCausality}, a novel benchmark specifically designed to evaluate the causal reasoning ability of VLMs in the temporal dimension. Based on our TimeCausality, we find that while the current SOTA open-source VLMs have achieved performance levels comparable to closed-source models like GPT-4o on various standard visual question answering tasks, they fall significantly behind on our benchmark compared with their closed-source competitors. Furthermore, even GPT-4o exhibits a marked drop in performance on TimeCausality compared to its results on other tasks. These findings underscore the critical need to incorporate temporal causality into the evaluation and development of VLMs, and they highlight an important challenge for the open-source VLM community moving forward. Code and Data are available at \href{https://github.com/Zeqing-Wang/TimeCausality }{TimeCausality}.

Jiaying Zhou, Zhihao Zhan, Ruifeng Zhai et al.

Vision--Language--Action (VLA) policies have shown strong progress in mapping language instructions and visual observations to robotic actions, yet their reliability degrades in cluttered scenes with distractors. By analyzing failure cases, we find that many errors do not arise from infeasible motions, but from instance-level grounding failures: the policy often produces a plausible grasp trajectory that lands slightly off-target or even on the wrong object instance. To address this issue, we propose TAG (Target-Agnostic Guidance), a simple inference-time guidance mechanism that explicitly reduces distractor- and appearance-induced bias in VLA policies. Inspired by classifier-free guidance (CFG), TAG contrasts policy predictions under the original observation and an object-erased observation, and uses their difference as a residual steering signal that strengthens the influence of object evidence in the decision process. TAG does not require modifying the policy architecture and can be integrated with existing VLA policies with minimal training and inference changes. We evaluate TAG on standard manipulation benchmarks, including LIBERO, LIBERO-Plus, and VLABench, where it consistently improves robustness under clutter and reduces near-miss and wrong-object executions.

Yijia Fan, Jusheng Zhang, Kaitong Cai et al.

Despite recent advancements in 3D-text cross-modal alignment, existing state-of-the-art methods still struggle to align fine-grained textual semantics with detailed geometric structures, and their alignment performance degrades significantly when scaling to large-scale 3D databases. To overcome this limitation, we introduce 3DAlign-DAER, a unified framework designed to align text and 3D geometry via the proposed dynamic attention policy and the efficient retrieval strategy, capturing subtle correspondences for diverse cross-modal retrieval and classification tasks. Specifically, during the training, our proposed dynamic attention policy (DAP) employs the Hierarchical Attention Fusion (HAF) module to represent the alignment as learnable fine-grained token-to-point attentions. To optimize these attentions across different tasks and geometric hierarchies, our DAP further exploits the Monte Carlo tree search to dynamically calibrate HAF attention weights via a hybrid reward signal and further enhances the alignment between textual descriptions and local 3D geometry. During the inference, our 3DAlign-DAER introduces an Efficient Retrieval Strategy (ERS) to leverage efficient hierarchical searching in the large-scale embedding spaces, outperforming traditional methods (e.g., KNN) in accuracy and efficiency. Furthermore, to facilitate text-3D alignment research and train our 3DAlign-DAER, we construct Align3D-2M, a large-scale dataset featuring 2M text-3D pairs, to provide sufficient fine-grained cross-modal annotations. Extensive and comprehensive experiments demonstrate the superior performance of our 3DAlign-DAER on diverse benchmarks. We will release our codes, models, and datasets.

Yang Liu, Keze Wang, Lingbo Liu et al.

Video self-supervised learning is a challenging task, which requires significant expressive power from the model to leverage rich spatial-temporal knowledge and generate effective supervisory signals from large amounts of unlabeled videos. However, existing methods fail to increase the temporal diversity of unlabeled videos and ignore elaborately modeling multi-scale temporal dependencies in an explicit way. To overcome these limitations, we take advantage of the multi-scale temporal dependencies within videos and proposes a novel video self-supervised learning framework named Temporal Contrastive Graph Learning (TCGL), which jointly models the inter-snippet and intra-snippet temporal dependencies for temporal representation learning with a hybrid graph contrastive learning strategy. Specifically, a Spatial-Temporal Knowledge Discovering (STKD) module is first introduced to extract motion-enhanced spatial-temporal representations from videos based on the frequency domain analysis of discrete cosine transform. To explicitly model multi-scale temporal dependencies of unlabeled videos, our TCGL integrates the prior knowledge about the frame and snippet orders into graph structures, i.e., the intra-/inter- snippet Temporal Contrastive Graphs (TCG). Then, specific contrastive learning modules are designed to maximize the agreement between nodes in different graph views. To generate supervisory signals for unlabeled videos, we introduce an Adaptive Snippet Order Prediction (ASOP) module which leverages the relational knowledge among video snippets to learn the global context representation and recalibrate the channel-wise features adaptively. Experimental results demonstrate the superiority of our TCGL over the state-of-the-art methods on large-scale action recognition and video retrieval benchmarks.The code is publicly available at https://github.com/YangLiu9208/TCGL.

Guangrun Wang, Keze Wang, Guangcong Wang et al.

Self-supervised learning (especially contrastive learning) has attracted great interest due to its huge potential in learning discriminative representations in an unsupervised manner. Despite the acknowledged successes, existing contrastive learning methods suffer from very low learning efficiency, e.g., taking about ten times more training epochs than supervised learning for comparable recognition accuracy. In this paper, we reveal two contradictory phenomena in contrastive learning that we call under-clustering and over-clustering problems, which are major obstacles to learning efficiency. Under-clustering means that the model cannot efficiently learn to discover the dissimilarity between inter-class samples when the negative sample pairs for contrastive learning are insufficient to differentiate all the actual object classes. Over-clustering implies that the model cannot efficiently learn features from excessive negative sample pairs, forcing the model to over-cluster samples of the same actual classes into different clusters. To simultaneously overcome these two problems, we propose a novel self-supervised learning framework using a truncated triplet loss. Precisely, we employ a triplet loss tending to maximize the relative distance between the positive pair and negative pairs to address the under-clustering problem; and we construct the negative pair by selecting a negative sample deputy from all negative samples to avoid the over-clustering problem, guaranteed by the Bernoulli Distribution model. We extensively evaluate our framework in several large-scale benchmarks (e.g., ImageNet, SYSU-30k, and COCO). The results demonstrate our model's superiority (e.g., the learning efficiency) over the latest state-of-the-art methods by a clear margin. Codes available at: https://github.com/wanggrun/triplet .

Junfan Lin, Zhongzhan Huang, Keze Wang et al.

Although deep reinforcement learning (RL) has been successfully applied to a variety of robotic control tasks, it's still challenging to apply it to real-world tasks, due to the poor sample efficiency. Attempting to overcome this shortcoming, several works focus on reusing the collected trajectory data during the training by decomposing them into a set of policy-irrelevant discrete transitions. However, their improvements are somewhat marginal since i) the amount of the transitions is usually small, and ii) the value assignment only happens in the joint states. To address these issues, this paper introduces a concise yet powerful method to construct Continuous Transition, which exploits the trajectory information by exploiting the potential transitions along the trajectory. Specifically, we propose to synthesize new transitions for training by linearly interpolating the consecutive transitions. To keep the constructed transitions authentic, we also develop a discriminator to guide the construction process automatically. Extensive experiments demonstrate that our proposed method achieves a significant improvement in sample efficiency on various complex continuous robotic control problems in MuJoCo and outperforms the advanced model-based / model-free RL methods. The source code is available.

Guangrun Wang, Keze Wang, Liang Lin

This paper presents a novel adaptively connected neural network (ACNet) to improve the traditional convolutional neural networks (CNNs) {in} two aspects. First, ACNet employs a flexible way to switch global and local inference in processing the internal feature representations by adaptively determining the connection status among the feature nodes (e.g., pixels of the feature maps) \footnote{In a computer vision domain, a node refers to a pixel of a feature map{, while} in {the} graph domain, a node denotes a graph node.}. We can show that existing CNNs, the classical multilayer perceptron (MLP), and the recently proposed non-local network (NLN) \cite{nonlocalnn17} are all special cases of ACNet. Second, ACNet is also capable of handling non-Euclidean data. Extensive experimental analyses on {a variety of benchmarks (i.e.,} ImageNet-1k classification, COCO 2017 detection and segmentation, CUHK03 person re-identification, CIFAR analysis, and Cora document categorization) demonstrate that {ACNet} cannot only achieve state-of-the-art performance but also overcome the limitation of the conventional MLP and CNN \footnote{Corresponding author: Liang Lin (linliang@ieee.org)}. The code is available at \url{https://github.com/wanggrun/Adaptively-Connected-Neural-Networks}.

Zhuojie Yang, Wentao Wan, Keze Wang

Training large language models (LLMs) with synthetic reasoning data has become a popular approach to enhancing their reasoning capabilities, while a key factor influencing the effectiveness of this paradigm is the quality of the generated multi-step reasoning data. To generate high-quality reasoning data, many recent methods generate synthetic reasoning paths and filter them based on final answer correctness, often overlooking flaws in intermediate reasoning steps. To enhance the verification of intermediate reasoning steps, prior work primarily resorts to code execution or symbolic reasoning engines. However, code-based validation is restricted to code or mathematical tasks, and reasoning engines require a well-structured and complete context. As a result, existing methods fail to function effectively in natural language reasoning tasks that involve ambiguous or incomplete contexts. In these tasks, synthetic data still lack reliable checks for verifying each reasoning step. To address this challenge, we introduce ORACLE, a structured data generation framework inspired by syllogistic reasoning. ORACLE integrates the generative strengths of LLMs with symbolic supervision: the LLM produces step-wise reasoning contexts, while a symbolic reasoning engine verifies the validity of each intermediate step. By employing a unified prompting template to elicit modular reasoning chains, ORACLE enables fine-grained, step-level validation, facilitating the construction of high-quality multi-step reasoning data. Across six logical, factual, and commonsense reasoning benchmarks, our ORACLE consistently outperforms strong baselines on multiple models.

Hui Fu, Zeqing Wang, Ke Gong et al.

Speech-driven 3D facial animation aims to synthesize vivid facial animations that accurately synchronize with speech and match the unique speaking style. However, existing works primarily focus on achieving precise lip synchronization while neglecting to model the subject-specific speaking style, often resulting in unrealistic facial animations. To the best of our knowledge, this work makes the first attempt to explore the coupled information between the speaking style and the semantic content in facial motions. Specifically, we introduce an innovative speaking style disentanglement method, which enables arbitrary-subject speaking style encoding and leads to a more realistic synthesis of speech-driven facial animations. Subsequently, we propose a novel framework called \textbf{Mimic} to learn disentangled representations of the speaking style and content from facial motions by building two latent spaces for style and content, respectively. Moreover, to facilitate disentangled representation learning, we introduce four well-designed constraints: an auxiliary style classifier, an auxiliary inverse classifier, a content contrastive loss, and a pair of latent cycle losses, which can effectively contribute to the construction of the identity-related style space and semantic-related content space. Extensive qualitative and quantitative experiments conducted on three publicly available datasets demonstrate that our approach outperforms state-of-the-art methods and is capable of capturing diverse speaking styles for speech-driven 3D facial animation. The source code and supplementary video are publicly available at: https://zeqing-wang.github.io/Mimic/

Jusheng Zhang, Yijia Fan, Wenjun Lin et al.

We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning. Unlike prior single-agent or monolithic models, GAM-Agent formulates the reasoning process as a non-zero-sum game between base agents--each specializing in visual perception subtasks--and a critical agent that verifies logic consistency and factual correctness. Agents communicate via structured claims, evidence, and uncertainty estimates. The framework introduces an uncertainty-aware controller to dynamically adjust agent collaboration, triggering multi-round debates when disagreement or ambiguity is detected. This process yields more robust and interpretable predictions. Experiments on four challenging benchmarks--MMMU, MMBench, MVBench, and V*Bench--demonstrate that GAM-Agent significantly improves performance across various VLM backbones. Notably, GAM-Agent boosts the accuracy of small-to-mid scale models (e.g., Qwen2.5-VL-7B, InternVL3-14B) by 5--6\%, and still enhances strong models like GPT-4o by up to 2--3\%. Our approach is modular, scalable, and generalizable, offering a path toward reliable and explainable multi-agent multimodal reasoning.

Jusheng Zhang, Kaitong Cai, Yijia Fan et al.

Recent advances in vision-language models (VLMs) have greatly improved cross-modal semantic understanding, yet significant limitations remain in fine-grained discrimination and deep causal reasoning tasks. Existing VLMs often rely on superficial statistical correlations, lacking the ability to capture the underlying causal logic between visual and textual content. To address this, we propose CounterFactual Vision-Language Fine-tuning (CF-VLM), a novel framework that enhances the causal reasoning capabilities of VLMs through the targeted use of counterfactual samples. CF-VLM introduces three complementary training objectives: maintaining foundational cross-modal alignment, reinforcing the uniqueness and stability of factual scene representations against coherent counterfactuals, and sharpening the model's sensitivity to minimal but critical causal edits. Extensive experiments demonstrate that CF-VLM consistently outperforms strong baselines and state-of-the-art methods on compositional reasoning and generalization benchmarks. Furthermore, it shows promise in mitigating visual hallucinations, indicating improved factual consistency. Our CF-VLM provides a robust foundation for deploying VLMs in high-stakes, real-world scenarios requiring reliable reasoning and interpretability.

Tianming Sha, Zechuan Chen, Zhan Cheng et al.

Stroke is an acute cerebrovascular disease, and timely diagnosis significantly improves patient survival. However, existing automated diagnosis methods suffer from fairness issues across demographic groups, potentially exacerbating healthcare disparities. In this work we propose FAST-CAD, a theoretically grounded framework that combines domain-adversarial training (DAT) with group distributionally robust optimization (Group-DRO) for fair and accurate non-contact stroke diagnosis. Our approach is built on domain adaptation and minimax fairness theory and provides convergence guarantees and fairness bounds. We curate a multimodal dataset covering 12 demographic subgroups defined by age, gender, and posture. FAST-CAD employs self-supervised encoders with adversarial domain discrimination to learn demographic-invariant representations, while Group-DRO optimizes worst-group risk to ensure robust performance across all subgroups. Extensive experiments show that our method achieves superior diagnostic performance while maintaining fairness across demographic groups, and our theoretical analysis supports the effectiveness of the unified DAT + Group-DRO framework. This work provides both practical advances and theoretical insights for fair medical AI systems.

Ziyi Tang, Zechuan Chen, Jiarui Yang et al.

Alpha mining, a critical component in quantitative investment, focuses on discovering predictive signals for future asset returns in increasingly complex financial markets. However, the pervasive issue of alpha decay, where factors lose their predictive power over time, poses a significant challenge for alpha mining. Traditional methods like genetic programming face rapid alpha decay from overfitting and complexity, while approaches driven by Large Language Models (LLMs), despite their promise, often rely too heavily on existing knowledge, creating homogeneous factors that worsen crowding and accelerate decay. To address this challenge, we propose AlphaAgent, an autonomous framework that effectively integrates LLM agents with ad hoc regularizations for mining decay-resistant alpha factors. AlphaAgent employs three key mechanisms: (i) originality enforcement through a similarity measure based on abstract syntax trees (ASTs) against existing alphas, (ii) hypothesis-factor alignment via LLM-evaluated semantic consistency between market hypotheses and generated factors, and (iii) complexity control via AST-based structural constraints, preventing over-engineered constructions that are prone to overfitting. These mechanisms collectively guide the alpha generation process to balance originality, financial rationale, and adaptability to evolving market conditions, mitigating the risk of alpha decay. Extensive evaluations show that AlphaAgent outperforms traditional and LLM-based methods in mitigating alpha decay across bull and bear markets, consistently delivering significant alpha in Chinese CSI 500 and US S&P 500 markets over the past four years. Notably, AlphaAgent showcases remarkable resistance to alpha decay, elevating the potential for yielding powerful factors.

Jusheng Zhang, Yijia Fan, Kaitong Cai et al.

This paper introduces DrDiff, a novel framework for long-text generation that overcomes the efficiency-quality trade-off through three core technologies. First, we design a dynamic expert scheduling mechanism that intelligently allocates computational resources during the diffusion process based on text complexity, enabling more efficient handling of text generation tasks of varying difficulty. Second, we introduce a Hierarchical Sparse Attention (HSA) mechanism that adaptively adjusts attention patterns according to a variety of input lengths, reducing computational complexity from O($n^2$) to O($n$) while maintaining model performance. Finally, we propose a soft absorption guidance optimization strategy that combines with DPM-solver++ to reduce diffusion steps, significantly improving generation speed. Comprehensive experiments on various long-text generation benchmarks demonstrate the superiority of our DrDiff over the existing SOTA methods.

Jusheng Zhang, Yijia Fan, Kaitong Cai et al.

This paper introduces OSC (Orchestrating Cognitive Synergy), a knowledge-aware adaptive collaboration framework designed to enhance cognitive synergy in multi-agent systems with large language models. While prior work has advanced agent selection and result aggregation, efficient linguistic interactions for deep collaboration among expert agents remain a critical bottleneck. OSC addresses this gap as a pivotal intermediate layer between selection and aggregation, introducing Collaborator Knowledge Models (CKM) to enable each agent to dynamically perceive its collaborators' cognitive states. Through real-time cognitive gap analysis, agents adaptively adjust communication behaviors, including content focus, detail level, and expression style, using learned strategies. Experiments on complex reasoning and problem-solving benchmarks demonstrate that OSC significantly improves task performance and communication efficiency, transforming "parallel-working individuals'' into a "deeply collaborative cognitive team.'' This framework not only optimizes multi-agent collaboration but also offers new insights into LLM agent interaction behaviors.

Jusheng Zhang, Zimeng Huang, Yijia Fan et al.

As scaling large language models faces prohibitive costs, multi-agent systems emerge as a promising alternative, though challenged by static knowledge assumptions and coordination inefficiencies. We introduces Knowledge-Aware Bayesian Bandits (KABB), a novel framework that enhances multi-agent system coordination through semantic understanding and dynamic adaptation. The framework features three key innovations: a three-dimensional knowledge distance model for deep semantic understanding, a dual-adaptation mechanism for continuous expert optimization, and a knowledge-aware Thompson Sampling strategy for efficient expert selection. Extensive evaluation demonstrates KABB achieves an optimal cost-performance balance, maintaining high performance while keeping computational demands relatively low in multi-agent coordination.

Jusheng Zhang, Kaitong Cai, Yijia Fan et al.

Multi-label image classification demands adaptive training strategies to navigate complex, evolving visual-semantic landscapes, yet conventional methods rely on static configurations that falter in dynamic settings. We propose MAT-Agent, a novel multi-agent framework that reimagines training as a collaborative, real-time optimization process. By deploying autonomous agents to dynamically tune data augmentation, optimizers, learning rates, and loss functions, MAT-Agent leverages non-stationary multi-armed bandit algorithms to balance exploration and exploitation, guided by a composite reward harmonizing accuracy, rare-class performance, and training stability. Enhanced with dual-rate exponential moving average smoothing and mixed-precision training, it ensures robustness and efficiency. Extensive experiments across Pascal VOC, COCO, and VG-256 demonstrate MAT-Agent's superiority: it achieves an mAP of 97.4 (vs. 96.2 for PAT-T), OF1 of 92.3, and CF1 of 91.4 on Pascal VOC; an mAP of 92.8 (vs. 92.0 for HSQ-CvN), OF1 of 88.2, and CF1 of 87.1 on COCO; and an mAP of 60.9, OF1 of 70.8, and CF1 of 61.1 on VG-256. With accelerated convergence and robust cross-domain generalization, MAT-Agent offers a scalable, intelligent solution for optimizing complex visual models, paving the way for adaptive deep learning advancements.