Searcharxiv⌕ Search

arXiv subjects

Keze Wang

Publications and source records attributed to Keze Wang.

At least 55 records · Page 3Linked to original sources
arXiv2026

3D-Agent:Tri-Modal Multi-Agent Collaboration for Scalable 3D Object Annotation

Driven by applications in autonomous driving robotics and augmented reality 3D object annotation presents challenges beyond 2D annotation including spatial complexity occlusion and viewpoint inconsistency Existing approaches based on single models often struggle to address these issues effectively We propose Tri MARF a novel framework that integrates tri modal inputs including 2D multi view images textual descriptions and 3D point clouds within a multi agent collaborative architecture to enhance large scale 3D annotation Tri MARF consists of three specialized agents a vision language model agent for generating multi view descriptions an information aggregation agent for selecting optimal descriptions and a gating agent that aligns textual semantics with 3D geometry for refined captioning Extensive experiments on Objaverse LVIS Objaverse XL and ABO demonstrate that Tri MARF substantially outperforms existing methods achieving a CLIPScore of 88 point 7 compared to prior state of the art methods retrieval accuracy of 45 point 2 and 43 point 8 on ViLT R at 5 and a throughput of up to 12000 objects per hour on a single NVIDIA A100 GPU

cs.CV↗
arXiv2025

Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention

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.

cs.CV↗
arXiv2025

CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation

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.

cs.CV↗
arXiv2025

Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains

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.

cs.CV↗
arXiv2025

RevFFN: Memory-Efficient Full-Parameter Fine-Tuning of Mixture-of-Experts LLMs with Reversible Blocks

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.

cs.LG↗
arXiv2025

SirenPose: Dynamic Scene Reconstruction via Geometric Supervision

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.

cs.CV↗
arXiv2025

FlashVLM: Text-Guided Visual Token Selection for Large Multimodal Models

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.

cs.CV↗
arXiv2025

Reflective Confidence: Correcting Reasoning Flaws via Online Self-Correction

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.

cs.AI↗
arXiv2025

PTTA: A Pure Text-to-Animation Framework for High-Quality Creation

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.

cs.CV↗
arXiv2025

LLM-CAS: Dynamic Neuron Perturbation for Real-Time Hallucination Correction

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.

cs.CL↗
arXiv2025

STORM: Search-Guided Generative World Models for Robotic Manipulation

We present STORM (Search-Guided Generative World Models), a novel framework for spatio-temporal reasoning in robotic manipulation that unifies diffusion-based action generation, conditional video prediction, and search-based planning. Unlike prior Vision-Language-Action (VLA) models that rely on abstract latent dynamics or delegate reasoning to language components, STORM grounds planning in explicit visual rollouts, enabling interpretable and foresight-driven decision-making. A diffusion-based VLA policy proposes diverse candidate actions, a generative video world model simulates their visual and reward outcomes, and Monte Carlo Tree Search (MCTS) selectively refines plans through lookahead evaluation. Experiments on the SimplerEnv manipulation benchmark demonstrate that STORM achieves a new state-of-the-art average success rate of 51.0 percent, outperforming strong baselines such as CogACT. Reward-augmented video prediction substantially improves spatio-temporal fidelity and task relevance, reducing Frechet Video Distance by over 75 percent. Moreover, STORM exhibits robust re-planning and failure recovery behavior, highlighting the advantages of search-guided generative world models for long-horizon robotic manipulation.

cs.RO↗
arXiv2025

Large Language Models as Discounted Bayesian Filters

Large Language Models (LLMs) demonstrate strong few-shot generalization through in-context learning, yet their reasoning in dynamic and stochastic environments remains opaque. Prior studies mainly focus on static tasks and overlook the online adaptation required when beliefs must be continuously updated, which is a key capability for LLMs acting as world models or agents. We introduce a Bayesian filtering framework to evaluate online inference in LLMs. Our probabilistic probe suite spans both multivariate discrete distributions, such as dice rolls, and continuous distributions, such as Gaussian processes, where ground-truth parameters shift over time. We find that while LLM belief updates resemble Bayesian posteriors, they are more accurately characterized by an exponential forgetting filter with a model-specific discount factor smaller than one. This reveals systematic discounting of older evidence that varies significantly across model architectures. Although inherent priors are often miscalibrated, the updating mechanism itself remains structured and principled. We further validate these findings in a simulated agent task and propose prompting strategies that effectively recalibrate priors with minimal computational cost.

cs.AI↗
arXiv2025

Adaptive-VoCo: Complexity-Aware Visual Token Compression for Vision-Language Models

In recent years, large-scale vision-language models (VLMs) have demonstrated remarkable performance on multimodal understanding and reasoning tasks. However, handling high-dimensional visual features often incurs substantial computational and memory costs. VoCo-LLaMA alleviates this issue by compressing visual patch tokens into a few VoCo tokens, reducing computational overhead while preserving strong cross-modal alignment. Nevertheless, such approaches typically adopt a fixed compression rate, limiting their ability to adapt to varying levels of visual complexity. To address this limitation, we propose Adaptive-VoCo, a framework that augments VoCo-LLaMA with a lightweight predictor for adaptive compression. This predictor dynamically selects an optimal compression rate by quantifying an image's visual complexity using statistical cues from the vision encoder, such as patch token entropy and attention map variance. Furthermore, we introduce a joint loss function that integrates rate regularization with complexity alignment. This enables the model to balance inference efficiency with representational capacity, particularly in challenging scenarios. Experimental results show that our method consistently outperforms fixed-rate baselines across multiple multimodal tasks, highlighting the potential of adaptive visual compression for creating more efficient and robust VLMs.

cs.CV↗
arXiv2025

GTMA: Dynamic Representation Optimization for OOD Vision-Language Models

Vision-language models (VLMs) struggle in open-world applications, where out-of-distribution (OOD) concepts often trigger cross-modal alignment collapse and severely degrade zero-shot performance. We identify the root cause as modal asymmetry: while the visual encoder can extract discriminative features from unseen images, the text encoder is constrained by a fixed discrete vocabulary and cannot synthesize new semantic anchors. Existing approaches such as CoOp or LoRA provide only partial remedies, as they remain confined to the pre-trained semantic space. To overcome this bottleneck, we propose dynamic representation optimization, realized through the Guided Target-Matching Adaptation (GTMA) framework. At inference time, GTMA constructs a continuous pseudo-word embedding that best aligns with an OOD image's visual anchor, effectively bypassing vocabulary limitations. The optimization is driven by an adaptive gradient-based representation policy optimization algorithm, which incorporates semantic regularization to preserve plausibility and compatibility with the model's prior knowledge. Experiments on ImageNet-R and the VISTA-Beyond benchmark demonstrate that GTMA improves zero-shot and few-shot OOD accuracy by up to 15-20 percent over the base VLM while maintaining performance on in-distribution concepts. Ablation studies further confirm the necessity of pseudo-word optimization.

cs.CV↗
arXiv2025

Enhancing Visual Programming for Visual Reasoning via Probabilistic Graphs

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.

cs.CV↗
arXiv2025

MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models

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.

cs.CV↗
arXiv2025

Causal Invariance and Counterfactual Learning Driven Cooperative Game for Multi-Label Classification

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.

cs.LG↗
arXiv2025

MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models

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.

cs.LG↗