论文检索

Xun Liang, Zhiying Li, Hongxun Jiang

This paper presents FAMDR, a Feature-Aligned Multimodal Denoising framework for Reliable Diagnostic Reconciliation. Existing approaches suffer from two major limitations: (1) an overemphasis on simplifying observational descriptions and (2) a failure to denoise the misleading content in radiological findings against clinical histories. Current methods often dismiss such cross-modal inconsistencies as noise rather than clinically significant signals. To bridge this gap, the framework integrates four synergistic components: (1) noise-aware multimodal alignment that preserves discriminative discrepancy features while ensuring semantic coherence, (2) cross-modal retrieval augmentation leveraging external medical knowledge to resolve ambiguous cases, (3) granular localization of noises at pixel and phrase levels using adaptive thresholding, and (4) medical noise uncertainty quantification to provide reliable confidence estimates. Evaluated on an extended MIMIC-CXR dataset enriched with expert-annotated noise and longitudinal records, FAMDR achieves superior accuracy in semantic denoising and inconsistency localization while preserving clinical interpretability. Its capability to generate actionable, uncertainty-aware reports advances safer and more reliable integration into diagnostic workflows.

Qian Liang, Yujia Wu, Kuncheng Li, Jiwei Wei, Shiyuan He, Jinyu Guo, Ning Xie

Multimodal Large Language Models (MLLMs) with unified architectures excel across a wide range of vision-language tasks, yet aligning them with personalized image generation remains a significant challenge. Existing methods for MLLMs are frequently subject-specific, demanding a data-intensive fine-tuning process for every new subject, which limits their scalability. In this paper, we introduce MM-R1, a framework that integrates a cross-modal Chain-of-Thought (X-CoT) reasoning strategy to unlock the inherent potential of unified MLLMs for personalized image generation. Specifically, we structure personalization as an integrated visual reasoning and generation process: (1) grounding subject concepts by interpreting and understanding user-provided images and contextual cues, and (2) generating personalized images conditioned on both the extracted subject representations and user prompts. To further enhance the reasoning capability, we adopt Grouped Reward Proximal Policy Optimization(GRPO) to explicitly align the generation. Experiments demonstrate that MM-R1 unleashes the personalization capability of unified MLLMs to generate images with high subject fidelity and strong text alignment in a zero-shot manner.

Jiaming Liang, Haowei Liu, Chi-Man Pun

Despite the tremendous success of neural networks, benign images can be corrupted by adversarial perturbations to deceive these models. Intriguingly, images differ in their attackability. Specifically, given an attack configuration, some images are easily corrupted, whereas others are more resistant. Evaluating image attackability has important applications in active learning, adversarial training, and attack enhancement. This prompts a growing interest in developing attackability measures. However, existing methods are scarce and suffer from two major limitations: (1) They rely on a model proxy to provide prior knowledge (e.g., gradients or minimal perturbation) to extract model-dependent image features. Unfortunately, in practice, many task-specific models are not readily accessible. (2) Extracted features characterizing image attackability lack visual interpretability, obscuring their direct relationship with the images. To address these, we propose a novel Object Texture Intensity (OTI), a model-free and visually interpretable measure of image attackability, which measures image attackability as the texture intensity of the image's semantic object. Theoretically, we describe the principles of OTI from the perspectives of decision boundaries as well as the mid- and high-frequency characteristics of adversarial perturbations. Comprehensive experiments demonstrate that OTI is effective and computationally efficient. In addition, our OTI provides the adversarial machine learning community with a visual understanding of attackability.

Yanhui Li, Yunkang Cao, Chengliang Liu, Yuan Xiong, Xinghui Dong, Chao Huang

Industrial anomaly detection is a critical component of modern manufacturing, yet the scarcity of defective samples restricts traditional detection methods to scenario-specific applications. Although Vision-Language Models (VLMs) demonstrate significant advantages in generalization capabilities, their performance in industrial anomaly detection remains limited. To address this challenge, we propose IAD-R1, a universal post-training framework applicable to VLMs of different architectures and parameter scales, which substantially enhances their anomaly detection capabilities. IAD-R1 employs a two-stage training strategy: the Perception Activation Supervised Fine-Tuning (PA-SFT) stage utilizes a meticulously constructed high-quality Chain-of-Thought dataset (Expert-AD) for training, enhancing anomaly perception capabilities and establishing reasoning-to-answer correlations; the Structured Control Group Relative Policy Optimization (SC-GRPO) stage employs carefully designed reward functions to achieve a capability leap from "Anomaly Perception" to "Anomaly Interpretation". Experimental results demonstrate that IAD-R1 achieves significant improvements across 7 VLMs, the largest improvement was on the DAGM dataset, with average accuracy 43.3% higher than the 0.5B baseline. Notably, the 0.5B parameter model trained with IAD-R1 surpasses commercial models including GPT-4.1 and Claude-Sonnet-4 in zero-shot settings, demonstrating the effectiveness and superiority of IAD-R1.

Xuchen Li, Xuzhao Li, Shiyu Hu, Kaiqi Huang, Wentao Zhang

Recent advances in large language models (LLMs) have improved reasoning in text and image domains, yet achieving robust video reasoning remains a significant challenge. Existing video benchmarks mainly assess shallow understanding and reasoning and allow models to exploit global context, failing to rigorously evaluate true causal and stepwise reasoning. We present CausalStep, a benchmark designed for explicit stepwise causal reasoning in videos. CausalStep segments videos into causally linked units and enforces a strict stepwise question-answer (QA) protocol, requiring sequential answers and preventing shortcut solutions. Each question includes carefully constructed distractors based on error type taxonomy to ensure diagnostic value. The benchmark features 100 videos across six categories and 1,852 multiple-choice QA pairs. We introduce seven diagnostic metrics for comprehensive evaluation, enabling precise diagnosis of causal reasoning capabilities. Experiments with leading proprietary and open-source models, as well as human baselines, reveal a significant gap between current models and human-level stepwise reasoning. CausalStep provides a rigorous benchmark to drive progress in robust and interpretable video reasoning.

Jiahao Li, Yang Lu, Yachao Zhang, Yong Xie, Fangyong Wang, Yuan Xie, Yanyun Qu

Open-vocabulary semantic segmentation (OVSS) employs pixel-level vision-language alignment to associate category-related prompts with corresponding pixels. A key challenge is enhancing the multimodal dense prediction capability, specifically this pixel-level multimodal alignment. Although existing methods achieve promising results by leveraging CLIP’s vision-language alignment, they rarely investigate the performance boundaries of CLIP for dense prediction from an interpretability mechanisms perspective. In this work, we systematically investigate CLIP's internal mechanisms and identify a critical phenomenon: analogous to human distraction, CLIP diverts significant attention resources from target regions to irrelevant tokens. Our analysis reveals that these tokens arise from dimension-specific over-activation; filtering them enhances CLIP's dense prediction performance. Consequently, we propose Refocusing CLIP (RF-CLIP), a training-free approach that emulates human distraction-refocusing behavior to redirect attention from distraction tokens back to target regions, thereby refining CLIP's multimodal alignment granularity. Our method achieves SOTA performance on eight benchmarks while maintaining high inference efficiency.

Hongxuan Li, Wencheng Zhu, Huiying Xu, Xinzhong Zhu, Pengfei Zhu

Vector quantization has emerged as a powerful tool in large-scale multimodal models, unifying heterogeneous representations through discrete token encoding. However, its effectiveness hinges on robust codebook design. Current prototype-based approaches relying on trainable vectors or clustered centroids fall short in representativeness and interpretability, even as multimodal alignment demonstrates its promise in vision-language models. To address these limitations, we propose a simple multimodal prompting-driven quantization framework for point cloud analysis. Our methodology is built upon two core insights: 1) Text embeddings from pre-trained models inherently encode visual semantics through many-to-one contrastive alignment, naturally serving as robust prototype priors; and 2) Multimodal prompts enable adaptive refinement of these prototypes, effectively mitigating vision-language semantic gaps. The framework introduces a dual-constrained quantization space, enforced by compactness and separation regularization, which seamlessly integrates visual and prototype features, resulting in hybrid representations that jointly encode geometric and semantic information. Furthermore, we employ Gumbel-Softmax relaxation to achieve differentiable discretization while maintaining quantization sparsity. Extensive experiments on the ModelNet40 and ScanObjectNN datasets clearly demonstrate the superior effectiveness of the proposed method.

Junhee Lee, ChaeBeen Bang, MyoungChul Kim, MyeongAh Cho

Weakly-Supervised Video Anomaly Detection aims to identify anomalous events using only video-level labels, balancing annotation efficiency with practical applicability. However, existing methods often oversimplify the anomaly space by treating all abnormal events as a single category, overlooking the diverse semantic and temporal characteristics intrinsic to real-world anomalies. Inspired by how humans perceive anomalies, by jointly interpreting temporal motion patterns and semantic structures underlying different anomaly types, we propose RefineVAD, a novel framework that mimics this dual-process reasoning. Our framework integrates two core modules. The first, Motion-aware Temporal Attention and Recalibration (MoTAR), estimates motion salience and dynamically adjusts temporal focus via shift-based attention and global Transformer-based modeling. The second, Category-Oriented Refinement (CORE), injects soft anomaly category priors into the representation space by aligning segment-level features with learnable category prototypes through cross-attention. By jointly leveraging temporal dynamics and semantic structure, explicitly models both ``how'' motion evolves and ``what'' semantic category it resembles. Extensive experiments on WVAD benchmark validate the effectiveness of RefineVAD and highlight the importance of integrating semantic context to guide feature refinement toward anomaly-relevant patterns.

Zengyuan Lai, Jiarui Yang, Songpengcheng Xia, Lizhou Lin, Lan Sun, Renwen Wang, Jianran Liu, Qi Wu, Ling Pei

Millimeter-wave radar offers a privacy-preserving and environment-robust alternative to vision-based sensing, enabling human motion analysis in challenging conditions such as low light, occlusions, rain, or smoke. However, its sparse point clouds pose significant challenges for semantic understanding. We present RadarLLM, the first framework that leverages large language models (LLMs) for human motion understanding from radar signals. RadarLLM introduces two key innovations: (1) a motion-guided radar tokenizer based on our Aggregate VQ-VAE architecture, integrating deformable body templates and masked trajectory modeling to convert spatial-temporal radar sequences into compact semantic tokens; and (2) a radar-aware language model that establishes cross-modal alignment between radar and text in a shared embedding space. To overcome the scarcity of paired radar-text data, we generate a realistic radar-text dataset from motion-text datasets with a physics-aware synthesis pipeline. Extensive experiments on both synthetic and real-world benchmarks show that RadarLLM achieves state-of-the-art performance, enabling robust and interpretable motion understanding under privacy and visibility constraints, even in adverse environments.

Yue Jiang, Haiwei Xue, Minghao Han, Mingcheng Li, Xiaolu Hou, Dingkang Yang, Lihua Zhang, Xu Zheng

Satire, a form of artistic expression combining humor with implicit critique, holds significant social value by illuminating societal issues. Despite its cultural and societal significance, satire comprehension, particularly in purely visual forms, remains a challenging task for current vision-language models. This task requires not only detecting satire but also deciphering its nuanced meaning and identifying the implicated entities. Existing models often fail to effectively integrate local entity relationships with global context, leading to misinterpretation, comprehension biases, and hallucinations. To address these limitations, we propose SatireDecoder, a training-free framework designed to enhance satirical image comprehension. Our approach proposes a multi-agent system performing visual cascaded decoupling to decompose images into fine-grained local and global semantic representations. In addition, we introduce a chain-of-thought reasoning strategy guided by uncertainty analysis, which breaks down the complex satire comprehension process into sequential subtasks with minimized uncertainty. Our method significantly improves interpretive accuracy while reducing hallucinations. Experimental results validate that SatireDecoder outperforms existing baselines in comprehending visual satire, offering a promising direction for vision-language reasoning in nuanced, high-level semantic tasks.

Lihong Huang, Sheng-hua Zhong, Zhi Zhang, Yan Liu

Recent advances in Referring Expression Comprehension (REC) have been largely driven by supervised learning on curated datasets, where each expression is assumed to refer to exactly one known object. However, such assumptions rarely hold in real-world scenarios, where expressions can refer to multiple objects, fail to refer to any, or involve novel categories and complex semantics. These challenges define the task of open-world REC, which demands robust generalization and structured reasoning beyond the scope of traditional REC methods. In this work, we introduce a novel, training-free framework that decouples visual perception from linguistic reasoning to address open-world REC. Our method first transforms the visual scene into a rich textual representation using an open-vocabulary multimodal perception module. It then employs a reasoning language model to interpret the referring expression and perform explicit logical inference over the perceived scene, enabling transparent decision-making and strong generalization in open-world scenarios. Experiments on three standard REC benchmarks as well as two more challenging ones, gRefCOCO and D³, demonstrate that our framework achieves highly competitive zero-shot performance, often surpassing supervised baselines.

Haojian Huang, Kaijing Ma, Jin Chen, Haodong Chen, Zhou Wu, Xianghao Zang, Han Fang, Chao Ban, Hao Sun, Mulin Chen 等

In the domain of moment retrieval, accurately identifying temporal segments within videos based on natural language queries remains challenging. Traditional methods often employ pre-trained models that struggle with fine-grained information and deterministic reasoning, leading to difficulties in aligning with complex or ambiguous moments. To overcome these limitations, we explore Deep Evidential Regression (DER) to construct a vanilla Evidential baseline. However, this approach encounters two major issues: the inability to effectively handle modality imbalance and the structural differences in DER's heuristic uncertainty regularizer, which adversely affect uncertainty estimation. This misalignment results in high uncertainty being incorrectly associated with accurate samples rather than challenging ones. Our observations indicate that existing methods lack the adaptability required for complex video scenarios. In response, we propose Debiased Evidential Learning for Moment Retrieval (DEMR), a novel framework that incorporates a Reflective Flipped Fusion (RFF) block for cross-modal alignment and a query reconstruction task to enhance text sensitivity, thereby reducing bias in uncertainty estimation. Additionally, we introduce a Geom-regularizer to refine uncertainty predictions, enabling adaptive alignment with difficult moments and improving retrieval accuracy. Extensive testing on standard datasets and debiased datasets ActivityNet-CD and Charades-CD demonstrates significant enhancements in effectiveness, robustness, and interpretability, positioning our approach as a promising solution for temporal-semantic robustness in moment retrieval.

Rishi Gupta, Mukilan Karuppasamy, Shyam Marjit, Aditay Tripathi, Anirban Chakraborty

While Large Vision Language Models (LVLMs) are increasingly deployed in real-world applications, their ability to interpret abstract visual inputs remains limited. Specifically, they struggle to comprehend hand-drawn sketches, a modality that offers an intuitive means of expressing concepts that are difficult to describe textually. We identify the primary bottleneck as the absence of a large-scale dataset that jointly models sketches, photorealistic images, and corresponding natural language instructions. To address this, we present two key contributions: (1) a new, large-scale dataset of image-sketch-instruction triplets designed to facilitate both pretraining and instruction tuning, and (2) O3SLM, an LVLM trained on this dataset. Comprehensive evaluations on multiple sketch-based tasks: (a) object localization, (b) counting, (c) image retrieval i.e., (SBIR and fine-grained SBIR), and (d) visual question answering (VQA); while incorporating the three existing sketch datasets, namely QuickDraw!, Sketchy, and Tu-Berlin, along with our generated SketchVCL dataset, show that O3SLM achieves state-of-the-art performance, substantially outperforming existing LVLMs in sketch comprehension and reasoning.

Shizhan Gong, Xiaofan Zhang, Qi Dou

Deep learning has achieved remarkable success in image recognition, yet their inherent opacity poses challenges for deployment in critical domains. Concept-based interpretations aim to address this by explaining model reasoning through human-understandable concepts. However, existing post-hoc methods and ante-hoc concept bottleneck models (CBMs), suffer from limitations such as unreliable concept relevance, non-visual or labor-intensive concept definitions, and model/data-agnostic assumptions. This paper introduces Post-hoc Concept Bottleneck Model via Representation Decomposition (PCBM-ReD), a novel pipeline that retrofits interpretability onto pretrained opaque models. PCBM-ReD automatically extracts visual concepts from a pre-trained encoder, employs multimodal large language models (MLLMs) to label and filter concepts based on visual identifiability and task relevance, and selects an independent subset via reconstruction-guided optimization. Leveraging CLIP’s visual-text alignment, it decomposes image representations into linear combination of concept embeddings to fit into the CBMs abstraction. Extensive experiments across 11 image classification tasks show PCBM-ReD achieves state-of-the-art accuracy, narrows the performance gap with end-to-end models, and exhibits better interpretability.

Tan Gao, Mufan Xue, Haofang Zheng, Shuo Lv, Jia Xu, Dabin Sheng, Ziming Mao, Xinyu Wu, Andrew Luo, Guoyuan Yang

Previous studies leveraging artificial neural networks have been used to investigate the semantic coding within human visual cortex. However, building an interpretable label-free framework that can effectively map brain responses to multiple coexisting semantic concepts remains largely unexplored. Here, we propose BrainLMM, a label-free framework for multi-semantic mapping of voxel responses by combining diverse vision encoders with the Describe-and-Dissect strategy, enabling a hypothesis-free analysis of the human high-level visual cortex. First, we construct voxel-wise encoding models leveraging diverse vision encoders to predict visual cortical responses to natural scene images. Then, we use BrainLMM to map individual brain voxels to multiple semantics without requiring any predefined labels. To evaluate the effectiveness of our method, we compute Pearson correlation coefficients to compare the multi-semantic mappings produced by BrainLMM and CLIP-MSM with ground-truth voxel responses within selective cortical areas. Our findings indicate that BrainLMM achieves more accurate predictions of visual responses compared to CLIP-MSM. Finally, to demonstrate the multi-semantic mapping capability of our method, we project multiple representative semantic concepts onto the cortical surface for visualization. Our method enables the discovery of voxels that exhibit strong activation in response to previously undefined semantic concepts across two independent datasets: the Natural Scenes Dataset (NSD) and the Natural Object Dataset (NOD).

Shibo Gao, Peipei Yang, Yangyang Liu, Yi Chen, Han Zhu, Xu-Yao Zhang, Linlin Huang

For video anomaly detection, it's both important to detect when the event happens and what the event is. The tasks of temporal grounding and semantic understanding can benefit from joint learning, but no existing work support it. To address this problem, we introduce VAGU (Video Anomaly Grounding and Understanding), the first benchmark designed to jointly evaluate semantic understanding and precise temporal grounding of anomalies, with comprehensive annotations and objective multiple-choice Video QA. Besides, we propose Glance then Scrutinize (GtS), the first training-free framework that achieves the best balance performance in both accuracy and efficiency. GtS uniquely balances high temporal precision and semantic interpretability while meeting practical speed requirements, outperforming previous methods in real-world scenarios. Furthermore, we introduce the JeAUG metric for holistic evaluation of both speed and accuracy. Extensive experiments demonstrate the superior effectiveness and practicality of our benchmark, framework, and metric.

Dawei Gao, Angello Huerta Gomez, Mingchen Li, Marcel El-Mokahal, Huaxiao Yang, Yunhe Feng

Accurately forecasting the spatiotemporal dynamics of biological systems, such as human pluripotent stem cell (hPSC)-derived cardiac organoids, from microscopy time-series is a critical challenge in biomedicine with profound implications for drug discovery. Existing generative models often fail to capture the intricate dynamics of organoid development, struggling with their irregular morphology, indistinct boundaries, and complex spatiotemporal patterns. To overcome these limitations, we introduce OrgaCast, a novel multimodal conditional diffusion model for high-fidelity organoid forecasting. OrgaCast uniquely conditions the generative process on three synergistic modalities: (i) historical image sequences, captured by a dedicated spatiotemporal control module; (ii) structured numerical metadata defining experimental conditions; and (iii) descriptive text captions summarizing the biological context. This comprehensive conditioning enables the generation of forecasts with high visual accuracy and biological plausibility. Furthermore, to enhance the model's utility in critical research settings, we introduce a post-hoc uncertainty quantification method that produces intuitive confidence maps, bolstering the interpretability and trustworthiness of predictions. Extensive experiments on a challenging cardiac organoid dataset demonstrate that OrgaCast outperforms baselines in metrics such as SSIM, PSNR, and LPIPS. Our framework presents a robust solution for biological forecasting, promising to accelerate research discovery while minimizing experimental costs and manual effort.

Dongjie Fu, Tengjiao Sun, Pengcheng Fang, Xiaohao Cai, Hansung Kim

Recent advances in transformer-based text-to-motion generation have significantly improved motion quality. However, achieving both real-time performance and long-horizon scalability remains an open challenge. In this paper, we present MOGO (Motion Generation with One-pass), a novel autoregressive framework for efficient and scalable 3D human motion generation. MOGO consists of two key components. First, we introduce MoSA-VQ, a motion scale-adaptive residual vector quantization module that hierarchically discretizes motion sequences through learnable scaling parameters, enabling dynamic allocation of representation capacity and producing compact yet expressive multi-level representations. Second, we design the RQHC-Transformer, a residual quantized hierarchical causal transformer that decodes motion tokens in a single forward pass. Each transformer block aligns with one quantization level, allowing hierarchical abstraction and temporally coherent generation with strong semantic flow. Compared to diffusion- and LLM-based approaches, MOGO achieves lower inference latency while preserving high motion fidelity. Moreover, its hierarchical latent design enables seamless and controllable infinite-length motion generation, with stable transitions and the ability to adaptively incorporate updated control signals at arbitrary points in time. To further enhance generalization and interpretability, we introduce Textual Condition Alignment (TCA), which leverages large language models with Chain-of-Thought reasoning to bridge the gap between real-world prompts and training data. TCA not only improves zero-shot performance on unseen datasets but also enriches motion comprehension for in-distribution prompts through explicit intent decomposition. Extensive experiments on HumanML3D, KIT-ML, and the unseen CMP dataset demonstrate that MOGO outperforms prior methods in generation quality, inference efficiency, and temporal scalability.

Kanglong Fan, Yunqiao Yang, Chen Ma

Deep neural networks have demonstrated remarkable performance across various domains, yet their decision-making processes remain opaque. Although many explanation methods are dedicated to bringing the obscurity of DNNs to light, they exhibit significant limitations: post-hoc explanation methods often struggle to faithfully reflect model behaviors, while self-explaining neural networks sacrifice performance and compatibility due to their specialized architectural designs. To address these challenges, we propose a novel self-explaining framework that integrates Shapley value estimation as an auxiliary task during training, which achieves two key advancements: 1) a fair allocation of the model prediction scores to image patches, ensuring explanations inherently align with the model's decision logic, and 2) enhanced interpretability with minor structural modifications, preserving model performance and compatibility. Extensive experiments on multiple benchmarks demonstrate that our method achieves state-of-the-art interpretability.

Yehonatan Elisha, Seffi Cohen, Oren Barkan, Noam Koenigstein

Saliency maps have become a cornerstone of visual explanation in deep learning, yet there remains no consensus on their intended purpose and their alignment with specific user queries. This fundamental ambiguity undermines both the evaluation and practical utility of explanation methods. In this paper, we introduce the Reference-Frame x Granularity (RFxG) taxonomy—a principled framework that addresses this ambiguity by conceptualizing saliency explanations along two essential axes: the reference-frame axis (distinguishing between pointwise "Why Husky?" and contrastive "Why Husky and not Shih-tzu?" explanations) and the granularity axis (ranging from fine-grained class-level to coarse-grained group-level interpretations, e.g., “Why Husky?” vs. “Why Dog?”). Through this lens, we identify critical limitations in existing evaluation metrics, which predominantly focus on pointwise faithfulness while neglecting contrastive reasoning and semantic granularity. To address these gaps, we propose four novel faithfulness metrics that systematically assess explanation quality across both RFxG dimensions. Our comprehensive evaluation framework spans ten state-of-the-art methods, 4 model architectures, and 3 datasets. By suggesting a shift from model-centric to user-intent-driven evaluation, our work provides both the conceptual foundation and practical tools necessary for developing explanations that are not only faithful to model behavior but also meaningfully aligned with human understanding.