arXiv subjects

Feilong Tang

Publications and source records attributed to Feilong Tang.

At least 37 records · Page 2Linked to original sources

arXiv2025

SAM-DCE: Addressing Token Uniformity and Semantic Over-Smoothing in Medical Segmentation

The Segment Anything Model (SAM) demonstrates impressive zero-shot segmentation ability on natural images but encounters difficulties in medical imaging due to domain shifts, anatomical variability, and its reliance on user-provided prompts. Recent prompt-free adaptations alleviate the need for expert intervention, yet still suffer from limited robustness and adaptability, often overlooking the issues of semantic over-smoothing and token uniformity. We propose SAM-DCE, which balances local discrimination and global semantics while mitigating token uniformity, enhancing inter-class separability, and enriching mask decoding with fine-grained, consistent representations. Extensive experiments on diverse medical benchmarks validate its effectiveness.

cs.CV↗

arXiv2025

ReconVLA: Reconstructive Vision-Language-Action Model as Effective Robot Perceiver

Recent advances in Vision-Language-Action (VLA) models have enabled robotic agents to integrate multimodal understanding with action execution. However, our empirical analysis reveals that current VLAs struggle to allocate visual attention to target regions. Instead, visual attention is always dispersed. To guide the visual attention grounding on the correct target, we propose ReconVLA, a reconstructive VLA model with an implicit grounding paradigm. Conditioned on the model's visual outputs, a diffusion transformer aims to reconstruct the gaze region of the image, which corresponds to the target manipulated objects. This process prompts the VLA model to learn fine-grained representations and accurately allocate visual attention, thus effectively leveraging task-specific visual information and conducting precise manipulation. Moreover, we curate a large-scale pretraining dataset comprising over 100k trajectories and 2 million data samples from open-source robotic datasets, further boosting the model's generalization in visual reconstruction. Extensive experiments in simulation and the real world demonstrate the superiority of our implicit grounding method, showcasing its capabilities of precise manipulation and generalization. Our project page is https://zionchow.github.io/ReconVLA/.

cs.RO↗

arXiv2025

MCA-LLaVA: Manhattan Causal Attention for Reducing Hallucination in Large Vision-Language Models

Hallucinations pose a significant challenge in Large Vision Language Models (LVLMs), with misalignment between multimodal features identified as a key contributing factor. This paper reveals the negative impact of the long-term decay in Rotary Position Encoding (RoPE), used for positional modeling in LVLMs, on multimodal alignment. Concretely, under long-term decay, instruction tokens exhibit uneven perception of image tokens located at different positions within the two-dimensional space: prioritizing image tokens from the bottom-right region since in the one-dimensional sequence, these tokens are positionally closer to the instruction tokens. This biased perception leads to insufficient image-instruction interaction and suboptimal multimodal alignment. We refer to this phenomenon as image alignment bias. To enhance instruction's perception of image tokens at different spatial locations, we propose MCA-LLaVA, based on Manhattan distance, which extends the long-term decay to a two-dimensional, multi-directional spatial decay. MCA-LLaVA integrates the one-dimensional sequence order and two-dimensional spatial position of image tokens for positional modeling, mitigating hallucinations by alleviating image alignment bias. Experimental results of MCA-LLaVA across various hallucination and general benchmarks demonstrate its effectiveness and generality. The code can be accessed in https://github.com/ErikZ719/MCA-LLaVA.

cs.CV↗

arXiv2025

Robust Multimodal Learning for Ophthalmic Disease Grading via Disentangled Representation

This paper discusses how ophthalmologists often rely on multimodal data to improve diagnostic accuracy. However, complete multimodal data is rare in real-world applications due to a lack of medical equipment and concerns about data privacy. Traditional deep learning methods typically address these issues by learning representations in latent space. However, the paper highlights two key limitations of these approaches: (i) Task-irrelevant redundant information (e.g., numerous slices) in complex modalities leads to significant redundancy in latent space representations. (ii) Overlapping multimodal representations make it difficult to extract unique features for each modality. To overcome these challenges, the authors propose the Essence-Point and Disentangle Representation Learning (EDRL) strategy, which integrates a self-distillation mechanism into an end-to-end framework to enhance feature selection and disentanglement for more robust multimodal learning. Specifically, the Essence-Point Representation Learning module selects discriminative features that improve disease grading performance. The Disentangled Representation Learning module separates multimodal data into modality-common and modality-unique representations, reducing feature entanglement and enhancing both robustness and interpretability in ophthalmic disease diagnosis. Experiments on multimodal ophthalmology datasets show that the proposed EDRL strategy significantly outperforms current state-of-the-art methods.

cs.CV↗

arXiv2025

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-confidence generations which often lead to persistent hallucinations. We introduce \textbf{Value-guided Inference with Margin-based Reward (ViMaR)}, a two-stage inference framework that improves both efficiency and output fidelity by combining a temporal-difference value model with a margin-aware reward adjustment. In the first stage, we perform a single pass to identify the highest-value caption among diverse candidates. In the second stage, we selectively refine only those segments that were overlooked or exhibit weak visual grounding, thereby eliminating frequently rewarded evaluations. A calibrated margin-based penalty discourages low-confidence continuations while preserving descriptive richness. Extensive experiments across multiple VLM architectures demonstrate that ViMaR generates captions that are significantly more reliable, factually accurate, detailed, and explanatory, while achieving over 4$\times$ speedup compared to existing value-guided methods. Specifically, we show that ViMaR trained solely on LLaVA Mistral-7B, \textit{generalizes effectively to guide decoding in a stronger unseen model}. To further validate this, we adapt the ViMaR to steer generation in LLaVA-OneVision-Qwen2-7B, leading to consistent improvements in caption quality and demonstrating robust cross-model guidance. This cross-model generalization highlights ViMaR's flexibility and modularity, positioning it as a scalable and transferable inference-time decoding strategy. Furthermore, when ViMaR-generated captions are used for self-training, the underlying models achieve substantial gains across a broad suite of visual comprehension benchmarks, underscoring the potential of fast, accurate, and self-improving VLM pipelines.

cs.CV↗

arXiv2025

RationalVLA: A Rational Vision-Language-Action Model with Dual System

A fundamental requirement for real-world robotic deployment is the ability to understand and respond to natural language instructions. Existing language-conditioned manipulation tasks typically assume that instructions are perfectly aligned with the environment. This assumption limits robustness and generalization in realistic scenarios where instructions may be ambiguous, irrelevant, or infeasible. To address this problem, we introduce RAtional MAnipulation (RAMA), a new benchmark that challenges models with both unseen executable instructions and defective ones that should be rejected. In RAMA, we construct a dataset with over 14,000 samples, including diverse defective instructions spanning six dimensions: visual, physical, semantic, motion, safety, and out-of-context. We further propose the Rational Vision-Language-Action model (RationalVLA). It is a dual system for robotic arms that integrates the high-level vision-language model with the low-level manipulation policy by introducing learnable latent space embeddings. This design enables RationalVLA to reason over instructions, reject infeasible commands, and execute manipulation effectively. Experiments demonstrate that RationalVLA outperforms state-of-the-art baselines on RAMA by a 14.5% higher success rate and 0.94 average task length, while maintaining competitive performance on standard manipulation tasks. Real-world trials further validate its effectiveness and robustness in practical applications. Our project page is https://irpn-eai.github.io/RationalVLA.

cs.RO↗

arXiv2025

Seeing Far and Clearly: Mitigating Hallucinations in MLLMs with Attention Causal Decoding

Recent advancements in multimodal large language models (MLLMs) have significantly improved performance in visual question answering. However, they often suffer from hallucinations. In this work, hallucinations are categorized into two main types: initial hallucinations and snowball hallucinations. We argue that adequate contextual information can be extracted directly from the token interaction process. Inspired by causal inference in the decoding strategy, we propose to leverage causal masks to establish information propagation between multimodal tokens. The hypothesis is that insufficient interaction between those tokens may lead the model to rely on outlier tokens, overlooking dense and rich contextual cues. Therefore, we propose to intervene in the propagation process by tackling outlier tokens to enhance in-context inference. With this goal, we present FarSight, a versatile plug-and-play decoding strategy to reduce attention interference from outlier tokens merely by optimizing the causal mask. The heart of our method is effective token propagation. We design an attention register structure within the upper triangular matrix of the causal mask, dynamically allocating attention to capture attention diverted to outlier tokens. Moreover, a positional awareness encoding method with a diminishing masking rate is proposed, allowing the model to attend to further preceding tokens, especially for video sequence tasks. With extensive experiments, FarSight demonstrates significant hallucination-mitigating performance across different MLLMs on both image and video benchmarks, proving its effectiveness.

cs.CV↗

arXiv2025

Confidence-Aware Self-Distillation for Multimodal Sentiment Analysis with Incomplete Modalities

Multimodal sentiment analysis (MSA) aims to understand human sentiment through multimodal data. In real-world scenarios, practical factors often lead to uncertain modality missingness. Existing methods for handling modality missingness are based on data reconstruction or common subspace projections. However, these methods neglect the confidence in multimodal combinations and impose constraints on intra-class representation, hindering the capture of modality-specific information and resulting in suboptimal performance. To address these challenges, we propose a Confidence-Aware Self-Distillation (CASD) strategy that effectively incorporates multimodal probabilistic embeddings via a mixture of Student's $t$-distributions, enhancing its robustness by incorporating confidence and accommodating heavy-tailed properties. This strategy estimates joint distributions with uncertainty scores and reduces uncertainty in the student network by consistency distillation. Furthermore, we introduce a reparameterization representation module that facilitates CASD in robust multimodal learning by sampling embeddings from the joint distribution for the prediction module to calculate the task loss. As a result, the directional constraint from the loss minimization is alleviated by the sampled representation. Experimental results on three benchmark datasets demonstrate that our method achieves state-of-the-art performance.

cs.LG↗

arXiv2025

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

Accurate 3D reconstruction of hands and instruments is critical for vision-based analysis of ophthalmic microsurgery, yet progress has been hampered by the lack of realistic, large-scale datasets and reliable annotation tools. In this work, we introduce OphNet-3D, the first extensive RGB-D dynamic 3D reconstruction dataset for ophthalmic surgery, comprising 41 sequences from 40 surgeons and totaling 7.1 million frames, with fine-grained annotations of 12 surgical phases, 10 instrument categories, dense MANO hand meshes, and full 6-DoF instrument poses. To scalably produce high-fidelity labels, we design a multi-stage automatic annotation pipeline that integrates multi-view data observation, data-driven motion prior with cross-view geometric consistency and biomechanical constraints, along with a combination of collision-aware interaction constraints for instrument interactions. Building upon OphNet-3D, we establish two challenging benchmarks-bimanual hand pose estimation and hand-instrument interaction reconstruction-and propose two dedicated architectures: H-Net for dual-hand mesh recovery and OH-Net for joint reconstruction of two-hand-two-instrument interactions. These models leverage a novel spatial reasoning module with weak-perspective camera modeling and collision-aware center-based representation. Both architectures outperform existing methods by substantial margins, achieving improvements of over 2mm in Mean Per Joint Position Error (MPJPE) and up to 23% in ADD-S metrics for hand and instrument reconstruction, respectively.

cs.CV↗

arXiv2025

DeepChest: Dynamic Gradient-Free Task Weighting for Effective Multi-Task Learning in Chest X-ray Classification

While Multi-Task Learning (MTL) offers inherent advantages in complex domains such as medical imaging by enabling shared representation learning, effectively balancing task contributions remains a significant challenge. This paper addresses this critical issue by introducing DeepChest, a novel, computationally efficient and effective dynamic task-weighting framework specifically designed for multi-label chest X-ray (CXR) classification. Unlike existing heuristic or gradient-based methods that often incur substantial overhead, DeepChest leverages a performance-driven weighting mechanism based on effective analysis of task-specific loss trends. Given a network architecture (e.g., ResNet18), our model-agnostic approach adaptively adjusts task importance without requiring gradient access, thereby significantly reducing memory usage and achieving a threefold increase in training speed. It can be easily applied to improve various state-of-the-art methods. Extensive experiments on a large-scale CXR dataset demonstrate that DeepChest not only outperforms state-of-the-art MTL methods by 7% in overall accuracy but also yields substantial reductions in individual task losses, indicating improved generalization and effective mitigation of negative transfer. The efficiency and performance gains of DeepChest pave the way for more practical and robust deployment of deep learning in critical medical diagnostic applications. The code is publicly available at https://github.com/youssefkhalil320/DeepChest-MTL

cs.CV↗

arXiv2025

ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos

Video diffusion models (VDMs) facilitate the generation of high-quality videos, with current research predominantly concentrated on scaling efforts during training through improvements in data quality, computational resources, and model complexity. However, inference-time scaling has received less attention, with most approaches restricting models to a single generation attempt. Recent studies have uncovered the existence of "golden noises" that can enhance video quality during generation. Building on this, we find that guiding the scaling inference-time search of VDMs to identify better noise candidates not only evaluates the quality of the frames generated in the current step but also preserves the high-level object features by referencing the anchor frame from previous multi-chunks, thereby delivering long-term value. Our analysis reveals that diffusion models inherently possess flexible adjustments of computation by varying denoising steps, and even a one-step denoising approach, when guided by a reward signal, yields significant long-term benefits. Based on the observation, we proposeScalingNoise, a plug-and-play inference-time search strategy that identifies golden initial noises for the diffusion sampling process to improve global content consistency and visual diversity. Specifically, we perform one-step denoising to convert initial noises into a clip and subsequently evaluate its long-term value, leveraging a reward model anchored by previously generated content. Moreover, to preserve diversity, we sample candidates from a tilted noise distribution that up-weights promising noises. In this way, ScalingNoise significantly reduces noise-induced errors, ensuring more coherent and spatiotemporally consistent video generation. Extensive experiments on benchmark datasets demonstrate that the proposed ScalingNoise effectively improves long video generation.

cs.LG↗

arXiv2025

TAGS: A Test-Time Generalist-Specialist Framework with Retrieval-Augmented Reasoning and Verification

Recent advances such as Chain-of-Thought prompting have significantly improved large language models (LLMs) in zero-shot medical reasoning. However, prompting-based methods often remain shallow and unstable, while fine-tuned medical LLMs suffer from poor generalization under distribution shifts and limited adaptability to unseen clinical scenarios. To address these limitations, we present TAGS, a test-time framework that combines a broadly capable generalist with a domain-specific specialist to offer complementary perspectives without any model fine-tuning or parameter updates. To support this generalist-specialist reasoning process, we introduce two auxiliary modules: a hierarchical retrieval mechanism that provides multi-scale exemplars by selecting examples based on both semantic and rationale-level similarity, and a reliability scorer that evaluates reasoning consistency to guide final answer aggregation. TAGS achieves strong performance across nine MedQA benchmarks, boosting GPT-4o accuracy by 13.8%, DeepSeek-R1 by 16.8%, and improving a vanilla 7B model from 14.1% to 23.9%. These results surpass several fine-tuned medical LLMs, without any parameter updates. The code will be available at https://github.com/JianghaoWu/TAGS.

cs.CL↗

arXiv2025

Rhythm of Opinion: A Hawkes-Graph Framework for Dynamic Propagation Analysis

The rapid development of social media has significantly reshaped the dynamics of public opinion, resulting in complex interactions that traditional models fail to effectively capture. To address this challenge, we propose an innovative approach that integrates multi-dimensional Hawkes processes with Graph Neural Network, modeling opinion propagation dynamics among nodes in a social network while considering the intricate hierarchical relationships between comments. The extended multi-dimensional Hawkes process captures the hierarchical structure, multi-dimensional interactions, and mutual influences across different topics, forming a complex propagation network. Moreover, recognizing the lack of high-quality datasets capable of comprehensively capturing the evolution of public opinion dynamics, we introduce a new dataset, VISTA. It includes 159 trending topics, corresponding to 47,207 posts, 327,015 second-level comments, and 29,578 third-level comments, covering diverse domains such as politics, entertainment, sports, health, and medicine. The dataset is annotated with detailed sentiment labels across 11 categories and clearly defined hierarchical relationships. When combined with our method, it offers strong interpretability by linking sentiment propagation to the comment hierarchy and temporal evolution. Our approach provides a robust baseline for future research.

cs.SI↗

arXiv2025

Beyond Words: AuralLLM and SignMST-C for Sign Language Production and Bidirectional Accessibility

Sign language is the primary communication mode for 72 million hearing-impaired individuals worldwide, necessitating effective bidirectional Sign Language Production and Sign Language Translation systems. However, functional bidirectional systems require a unified linguistic environment, hindered by the lack of suitable unified datasets, particularly those providing the necessary pose information for accurate Sign Language Production (SLP) evaluation. Concurrently, current SLP evaluation methods like back-translation ignore pose accuracy, and high-quality coordinated generation remains challenging. To create this crucial environment and overcome these challenges, we introduce CNText2Sign and CNSign, which together constitute the first unified dataset aimed at supporting bidirectional accessibility systems for Chinese sign language; CNText2Sign provides 15,000 natural language-to-sign mappings and standardized skeletal keypoints for 8,643 vocabulary items supporting pose assessment. Building upon this foundation, we propose the AuraLLM model, which leverages a decoupled architecture with CNText2Sign's pose data for novel direct gesture accuracy assessment. The model employs retrieval augmentation and Cascading Vocabulary Resolution to handle semantic mapping and out-of-vocabulary words and achieves all-scenario production with controllable coordination of gestures and facial expressions via pose-conditioned video synthesis. Concurrently, our Sign Language Translation model SignMST-C employs targeted self-supervised pretraining for dynamic feature capture, achieving new SOTA results on PHOENIX2014-T with BLEU-4 scores up to 32.08. AuraLLM establishes a strong performance baseline on CNText2Sign with a BLEU-4 score of 50.41 under direct evaluation.

cs.CV↗

arXiv2025

PG-SAM: Prior-Guided SAM with Medical for Multi-organ Segmentation

Segment Anything Model (SAM) demonstrates powerful zero-shot capabilities; however, its accuracy and robustness significantly decrease when applied to medical image segmentation. Existing methods address this issue through modality fusion, integrating textual and image information to provide more detailed priors. In this study, we argue that the granularity of text and the domain gap affect the accuracy of the priors. Furthermore, the discrepancy between high-level abstract semantics and pixel-level boundary details in images can introduce noise into the fusion process. To address this, we propose Prior-Guided SAM (PG-SAM), which employs a fine-grained modality prior aligner to leverage specialized medical knowledge for better modality alignment. The core of our method lies in efficiently addressing the domain gap with fine-grained text from a medical LLM. Meanwhile, it also enhances the priors' quality after modality alignment, ensuring more accurate segmentation. In addition, our decoder enhances the model's expressive capabilities through multi-level feature fusion and iterative mask optimizer operations, supporting unprompted learning. We also propose a unified pipeline that effectively supplies high-quality semantic information to SAM. Extensive experiments on the Synapse dataset demonstrate that the proposed PG-SAM achieves state-of-the-art performance. Our code is released at https://github.com/logan-0623/PG-SAM.

cs.CV↗

arXiv2025

Exploring CLIP's Dense Knowledge for Weakly Supervised Semantic Segmentation

Weakly Supervised Semantic Segmentation (WSSS) with image-level labels aims to achieve pixel-level predictions using Class Activation Maps (CAMs). Recently, Contrastive Language-Image Pre-training (CLIP) has been introduced in WSSS. However, recent methods primarily focus on image-text alignment for CAM generation, while CLIP's potential in patch-text alignment remains unexplored. In this work, we propose ExCEL to explore CLIP's dense knowledge via a novel patch-text alignment paradigm for WSSS. Specifically, we propose Text Semantic Enrichment (TSE) and Visual Calibration (VC) modules to improve the dense alignment across both text and vision modalities. To make text embeddings semantically informative, our TSE module applies Large Language Models (LLMs) to build a dataset-wide knowledge base and enriches the text representations with an implicit attribute-hunting process. To mine fine-grained knowledge from visual features, our VC module first proposes Static Visual Calibration (SVC) to propagate fine-grained knowledge in a non-parametric manner. Then Learnable Visual Calibration (LVC) is further proposed to dynamically shift the frozen features towards distributions with diverse semantics. With these enhancements, ExCEL not only retains CLIP's training-free advantages but also significantly outperforms other state-of-the-art methods with much less training cost on PASCAL VOC and MS COCO.

cs.CV↗

arXiv2025

VideoGen-of-Thought: Step-by-step generating multi-shot video with minimal manual intervention

Current video generation models excel at short clips but fail to produce cohesive multi-shot narratives due to disjointed visual dynamics and fractured storylines. Existing solutions either rely on extensive manual scripting/editing or prioritize single-shot fidelity over cross-scene continuity, limiting their practicality for movie-like content. We introduce VideoGen-of-Thought (VGoT), a step-by-step framework that automates multi-shot video synthesis from a single sentence by systematically addressing three core challenges: (1) Narrative Fragmentation: Existing methods lack structured storytelling. We propose dynamic storyline modeling, which first converts the user prompt into concise shot descriptions, then elaborates them into detailed, cinematic specifications across five domains (character dynamics, background continuity, relationship evolution, camera movements, HDR lighting), ensuring logical narrative progression with self-validation. (2) Visual Inconsistency: Existing approaches struggle with maintaining visual consistency across shots. Our identity-aware cross-shot propagation generates identity-preserving portrait (IPP) tokens that maintain character fidelity while allowing trait variations (expressions, aging) dictated by the storyline. (3) Transition Artifacts: Abrupt shot changes disrupt immersion. Our adjacent latent transition mechanisms implement boundary-aware reset strategies that process adjacent shots' features at transition points, enabling seamless visual flow while preserving narrative continuity. VGoT generates multi-shot videos that outperform state-of-the-art baselines by 20.4% in within-shot face consistency and 17.4% in style consistency, while achieving over 100% better cross-shot consistency and 10x fewer manual adjustments than alternatives.

cs.CV↗

arXiv2025

Unveiling the Ignorance of MLLMs: Seeing Clearly, Answering Incorrectly

Multimodal Large Language Models (MLLMs) have displayed remarkable performance in multi-modal tasks, particularly in visual comprehension. However, we reveal that MLLMs often generate incorrect answers even when they understand the visual content. To this end, we manually construct a benchmark with 12 categories and design evaluation metrics that assess the degree of error in MLLM responses even when the visual content is seemingly understood. Based on this benchmark, we test 15 leading MLLMs and analyze the distribution of attention maps and logits of some MLLMs. Our investigation identifies two primary issues: 1) most instruction tuning datasets predominantly feature questions that 'directly' relate to the visual content, leading to a bias in MLLMs' responses to other indirect questions, and 2) MLLMs' attention to visual tokens is notably lower than to system and question tokens. We further observe that attention scores between questions and visual tokens as well as the model's confidence in the answers are lower in response to misleading questions than to straightforward ones. To address the first challenge, we introduce a paired positive and negative data construction pipeline to diversify the dataset. For the second challenge, we propose to enhance the model's focus on visual content during decoding by refining the text and visual prompt. For the text prompt, we propose a content guided refinement strategy that performs preliminary visual content analysis to generate structured information before answering the question. Additionally, we employ a visual attention refinement strategy that highlights question-relevant visual tokens to increase the model's attention to visual content that aligns with the question. Extensive experiments demonstrate that these challenges can be significantly mitigated with our proposed dataset and techniques.

cs.CV↗