Multimodal

Complex question answering across text, tables and images requires integrating diverse information sources. A framework supporting specialized processing with coordination and interpretability is needed. We introduce DeALOG, a decentralized multi-agent framework for multimodal question answering. It uses specialized agents: Table, Context, Visual, Summarizing and Verification, that communicate through a shared natural-language log as persistent memory. This log-based approach enables collaborative error detection and verification without central control, improving robustness. Evaluations on FinQA, TAT-QA, CRT-QA, WikiTableQuestions, FeTaQA, and MultiModalQA show competitive performance. Analysis confirms the importance of the shared log, agent specialization, and verification for accuracy. DeALOG, provides a scalable approach through modular components using natural-language communication.

Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their grasp of temporal dynamics remains brittle. We present TimeBlind, a diagnostic benchmark for compositional spatio-temporal understanding. Inspired by cognitive science, TimeBlind categorizes fine-grained temporal understanding into three levels: recognizing atomic events, characterizing event properties, and reasoning about event interdependencies. Unlike benchmarks that conflate recognition with temporal reasoning, TimeBlind leverages a minimal-pairs paradigm: video pairs share identical static visual content but differ solely in temporal structure, utilizing complementary questions to neutralize language priors. Evaluating over 20 state-of-the-art MLLMs (e.g., GPT-5, Gemini 3 Pro) on 600 curated instances (2400 video-question pairs), reveals that the Instance Accuracy (correctly distinguishing both videos in a pair) of the best performing MLLM is only 48.2%, far below the human performance (98.2%). These results demonstrate that even frontier models rely heavily on static visual shortcuts rather than genuine temporal logic, positioning TimeBlind as a vital diagnostic tool for next-generation video understanding. Dataset and code are available at https://baiqi-li.github.io/timeblind_project/ .

With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in complex and dynamic industrial sites has become a key bottleneck for deploying predictive maintenance and autonomous inspection. Most public datasets remain limited by simulated data sources, single-modality sensing, or the absence of fine-grained object-level annotations, which prevents robust scene understanding and multimodal safety reasoning for industrial foundation models. To address these limitations, InspecSafe-V1 is released as the first multimodal benchmark dataset for industrial inspection safety assessment that is collected from routine operations of real inspection robots in real-world environments. InspecSafe-V1 covers five representative industrial scenarios, including tunnels, power facilities, sintering equipment, oil and gas petrochemical plants, and coal conveyor trestles. The dataset is constructed from 41 wheeled and rail-mounted inspection robots operating at 2,239 valid inspection sites, yielding 5,013 inspection instances. For each instance, pixel-level segmentation annotations are provided for key objects in visible-spectrum images. In addition, a semantic scene description and a corresponding safety level label are provided according to practical inspection tasks. Seven synchronized sensing modalities are further included, including infrared video, audio, depth point clouds, radar point clouds, gas measurements, temperature, and humidity, to support multimodal anomaly recognition, cross-modal fusion, and comprehensive safety assessment in industrial environments.

Deepfake detection is a widely researched topic that is crucial for combating the spread of malicious content, with existing methods mainly modeling the problem as classification or spatial localization. The rapid advancements in generative models impose new demands on Deepfake detection. In this paper, we propose multimodal alignment and reinforcement for explainable Deepfake detection via vision-language models, termed MARE, which aims to enhance the accuracy and reliability of Vision-Language Models (VLMs) in Deepfake detection and reasoning. Specifically, MARE designs comprehensive reward functions, incorporating reinforcement learning from human feedback (RLHF), to incentivize the generation of text-spatially aligned reasoning content that adheres to human preferences. Besides, MARE introduces a forgery disentanglement module to capture intrinsic forgery traces from high-level facial semantics, thereby improving its authenticity detection capability. We conduct thorough evaluations on the reasoning content generated by MARE. Both quantitative and qualitative experimental results demonstrate that MARE achieves state-of-the-art performance in terms of accuracy and reliability.

While InfoNCE underlies modern contrastive learning, its geometric mechanisms remain under-characterized beyond the canonical alignment--uniformity decomposition. We develop a measure-theoretic framework in which representation measures evolve on a fixed embedding manifold. In the large-batch limit, we prove value and gradient consistency, linking the stochastic objective to explicit deterministic energy landscapes and revealing a geometric bifurcation between unimodal and symmetric multimodal regimes. In the unimodal case, the intrinsic energy is strictly convex and admits a unique Gibbs equilibrium, showing that entropy acts as a tie-breaker within the aligned basin. In the multimodal case, the intrinsic geometry becomes cross-coupled and contains a persistent negative symmetric divergence term: each modality's marginal reshapes the effective landscape of the other, allowing strong pairwise alignment to coexist with a persistent modality gap. Controlled synthetic experiments and analyses of pretrained CLIP representations support these predictions. Overall, our results shift the analytical lens from pointwise discrimination to population geometry, showing that pairwise alignment alone is insufficient to control cross-modal marginal structure.

Recent advances in multi-modal detection have significantly improved detection accuracy in challenging environments (e.g., low light, overexposure). By integrating RGB with modalities such as thermal and depth, multi-modal fusion increases data redundancy and system robustness. However, significant challenges remain in effectively extracting task-relevant information both within and across modalities, as well as in achieving precise cross-modal alignment. While CNNs excel at feature extraction, they are limited by constrained receptive fields, strong inductive biases, and difficulty in capturing long-range dependencies. Transformer-based models offer global context but suffer from quadratic computational complexity and are confined to pairwise correlation modeling. Mamba and other State Space Models (SSMs), on the other hand, are hindered by their sequential scanning mechanism, which flattens 2D spatial structures into 1D sequences, disrupting topological relationships and limiting the modeling of complex higher-order dependencies. To address these issues, we propose a multi-modal perception network based on hypergraph theory called M2I2HA. Our architecture includes an Intra-Hypergraph Enhancement module to capture global many-to-many high-order relationships within each modality, and an Inter-Hypergraph Fusion module to align, enhance, and fuse cross-modal features by bridging configuration and spatial gaps between data sources. We further introduce a M2-FullPAD module to enable adaptive multi-level fusion of multi-modal enhanced features within the network, meanwhile enhancing data distribution and flow across the architecture. Extensive object detection experiments on multiple public datasets against baselines demonstrate that M2I2HA achieves state-of-the-art performance in multi-modal object detection tasks.

Social understanding abilities are crucial for multimodal large language models (MLLMs) to interpret human social interactions. We introduce SOCIAL CAPTION, a framework grounded in interaction theory to evaluate social understanding abilities of MLLMs along three dimensions: Social Inference (SI), the ability to make accurate inferences about interactions; Holistic Social Analysis (HSA), the ability to generate comprehensive descriptions of interactions; Directed Social Analysis (DSA), the ability to generate relevant information from interactions. We analyze factors influencing model performance in social understanding, such as scale, architectural design, and spoken context. Experiments with MLLM judges demonstrate a path towards scaling automated evaluation of multimodal social understanding.

We investigate visual reasoning limitations of both multimodal large language models (MLLMs) and image generation models (IGMs) by creating a novel benchmark to systematically compare failure modes across image-to-text and text-to-image tasks, enabling cross-modal evaluation of visual understanding. Despite rapid growth in machine learning, vision language models (VLMs) still fail to understand basic visual concepts such as object orientation, quantity, and spatial relationships, which highlights gaps in elementary visual reasoning. By adapting MMVP benchmark questions into explicit and implicit prompts, we create \textit{AMVICC}, a novel benchmark for profiling failure modes across various modalities. After testing 11 MLLMs and 3 IGMs in 9 categories of visual reasoning, our results show that failure modes are often shared between models and modalities. However, certain failures are model-specific and modality-specific, and this can potentially be attributed to various factors. IGMs consistently struggle to manipulate specific visual components in response to prompts, especially in explicit prompts, suggesting poor control over fine-grained visual attributes. Our findings apply most directly to the evaluation of existing state-of-the-art models on structured visual reasoning tasks. This work lays the foundation for future cross-modal alignment studies, offering a framework to probe whether image generation and visual interpretation failures stem from shared limitations. These insights can guide future improvements in unified vision-language modeling.

Multimodal large language models (MLLMs) are increasingly used to automate chart generation from data tables, improving efficiency but introducing new misuse risks. We present ChartAttack, a framework for evaluating how MLLMs use design misleaders to generate charts that induce incorrect interpretations. We also introduce AttackViz, a chart question-answering (QA) dataset labeled with effective misleaders and their induced incorrect answers. ChartAttack reduces MLLM QA accuracy by 17.2 points in-domain and 11.9 points cross-domain. Conditional deception rates show targeted effects: correct answers shift to attacker-intended answers 11.2% of the time in-domain and 11.7-14.9% cross-domain, while originally incorrect answers rarely change. A controlled human study shows that ChartAttack-generated charts also reduce human QA performance. Finally, fine-tuning on AttackViz improves in-domain MLLM robustness to misleading charts. Our findings highlight the need for secure, robust MLLM chart generation. Code and data are publicly available on the project website.

The core of video-based visible-infrared person re-identification (VVI-ReID) lies in learning sequence-level modal-invariant representations across different modalities. Recent research tends to use modality-shared language prompts generated by CLIP to guide the learning of modal-invariant representations. Despite achieving optimal performance, such methods still face limitations in efficient spatial-temporal modeling, sufficient cross-modal interaction, and explicit modality-level loss guidance. To address these issues, we propose the language-driven sequence-level modal-invariant representation learning (LSMRL) method, which includes spatial-temporal feature learning (STFL) module, semantic diffusion (SD) module and cross-modal interaction (CMI) module. To enable parameter- and computation-efficient spatial-temporal modeling, the STFL module is built upon CLIP with minimal modifications. To achieve sufficient cross-modal interaction and enhance the learning of modal-invariant features, the SD module is proposed to diffuse modality-shared language prompts into visible and infrared features to establish preliminary modal consistency. The CMI module is further developed to leverage bidirectional cross-modal self-attention to eliminate residual modality gaps and refine modal-invariant representations. To explicitly enhance the learning of modal-invariant representations, two modality-level losses are introduced to improve the features' discriminative ability and their generalization to unseen categories. Extensive experiments on large-scale VVI-ReID datasets demonstrate the superiority of LSMRL over AOTA methods.

Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoning remains unstable. Repeated sampling over the same input often produces divergent reasoning trajectories and inconsistent final predictions. To address this, we introduce two complementary approaches inspired by test-time scaling: (1) CASHEW, an inference-time framework that stabilizes reasoning by iteratively aggregating multiple candidate trajectories into higher-quality reasoning traces, with explicit visual verification filtering hallucinated steps and grounding reasoning in visual evidence, and (2) CASHEW-RL, a learned variant that internalizes this aggregation behavior within a single model. CASHEW-RL is trained using Group Sequence Policy Optimization (GSPO) with a composite reward that encourages correct answers grounded in minimal yet sufficient visual evidence, while adaptively allocating reasoning effort based on task difficulty. This training objective enables robust self-aggregation at inference. Extensive experiments on 13 image understanding, video understanding, and video reasoning benchmarks show significant performance improvements, including gains of up to +26.2 percentage points on ScienceQA and +9.1 percentage points on EgoSchema.

Vision Language Models (VLMs) have demonstrated remarkable potential in multimodal reasoning. However, they can have spatial blindness and logical hallucinations when interpreting densely structured engineering content, such as analog circuit schematics. To address these challenges, we propose a Vision Language Model-Optimized Collaborative Agent Design Workflow for Analog Circuit Sizing (VLM-CAD) designed to support step-by-step reasoning over multimodal evidence. VLM-CAD bridges the modality gap by integrating a neuro-symbolic structural parsing module, Image2Net, which transforms raw pixels into explicit topological graphs and structured JSON representations to anchor VLM interpretation in deterministic facts. To ensure the reliability required for engineering decisions, we further propose ExTuRBO, an Explainable Trust Region Bayesian Optimization method. ExTuRBO employs agent-generated semantic seeds to warm-start local searches and uses Automatic Relevance Determination to provide sensitivity evidence for the final design report. Experimental results on 12 sizing tasks covering six circuits and four technology platforms show that VLM-CAD achieves a pooled Strict Pass@1 of 23.3% and a Relaxed Pass@1 of 91.7%, while providing sensitivity evidence for final design reports.

Contrastive Language-Image Pre-training (CLIP) relies on Vision Transformers whose attention mechanism is susceptible to spurious correlations, and scales quadratically with resolution. To address these limitations, We present CLIMP, the first fully Mamba-based contrastive vision-language model that replaces both the vision and text encoders with Mamba. The new architecture encodes sequential structure in both vision and language, with VMamba capturing visual spatial inductive biases, reducing reliance on spurious correlations and producing an embedding space favorable for cross-modal retrieval and out-of-distribution robustness-surpassing OpenAI's CLIP-ViT-B by 7.5% on ImageNet-O. CLIMP naturally supports variable input resolutions without positional encoding interpolation or specialized training, achieving up to 6.6% higher retrieval accuracy at 16x training resolution while using 5x less memory and 1.8x fewer FLOPs. The autoregressive text encoder further overcomes CLIP's fixed context limitation, enabling dense captioning retrieval. Our findings suggest that Mamba exhibits advantageous properties for vision-language learning, making it a compelling alternative to Transformer-based CLIP.The code and models are publicly available at https://github.com/NimrodShabtay/CLIMP}

Semantic Multi-Object Tracking (SMOT) is evolving from purely geometric localization toward comprehensive video understanding. However, existing paradigms predominantly rely on closed-set interaction tags and fragmented perception pipelines, creating a bottleneck that prevents the full utilization of Multi-modal Large Language Models (MLLMs) for dynamic scenes. In this paper, we elevate SMOT from rigid classification to an open-ended generative reasoning task. To support this paradigm shift, we introduce Grand-SMOT, a large-scale benchmark featuring high-density, dual-stream narratives. This dataset explicitly decouples micro-level individual dynamics from macro-level environmental contexts, directly resolving the semantic scarcity of prior tracking datasets. Furthermore, we propose LLMTrack, a unified MLLM-driven framework for dynamic SMOT. Guided by a verifiable ``\textit{Macro-Understanding-First}'' mechanism, LLMTrack employs a Spatio-Temporal Fusion Module to compress discrete geometric trajectories into continuous semantic tokens, effectively suppressing temporal hallucinations in long-sequence tracking. Extensive experiments, utilizing a novel decoupled evaluation protocol, validate that LLMTrack achieves state-of-the-art geometric tracking robustness while delivering a qualitative leap in generative semantic reasoning. The code and datasets are publicly available at https://github.com/liaopan-lp/LLMTrack-GrandSMOT.

While humans develop core visual skills long before acquiring language, contemporary Multimodal LLMs (MLLMs) still rely heavily on linguistic priors to compensate for their fragile visual understanding. We uncovered a crucial fact: state-of-the-art MLLMs consistently fail on basic visual tasks that humans, even 3-year-olds, can solve effortlessly. To systematically investigate this gap, we introduce BabyVision, a benchmark designed to assess core visual abilities independent of linguistic knowledge for MLLMs. BabyVision spans a wide range of tasks, with 388 items divided into 22 subclasses across four key categories. Empirical results and human evaluation reveal that leading MLLMs perform significantly below human baselines. Gemini3-Pro-Preview scores 49.7, lagging behind 6-year-old humans and falling well behind the average adult score of 94.1. These results show despite excelling in knowledge-heavy evaluations, current MLLMs still lack fundamental visual primitives. Progress in BabyVision represents a step toward human-level visual perception and reasoning capabilities. We also explore solving visual reasoning with generation models by proposing BabyVision-Gen and automatic evaluation toolkit. Our code and benchmark data are released at https://github.com/UniPat-AI/BabyVision for reproduction.

Despite remarkable capability in multi-modal understanding, deploying Multi-modal Large Language Models (MLLMs) in open-ended conversational scenarios introduces safety risks that remain poorly addressed by existing alignment methods. Unlike simple malicious visual question and answer (VQA) pairs , multi-turn interactions enable adversaries to incrementally reconstruct harmful intent across dialogues, progressively bypassing safety constraints in ways that are difficult to detect at any individual turn. Meanwhile, conventional reinforcement learning from human feedback (RLHF) approaches are unsuitable for this situation: designed primarily for VQA tasks, they neither capture cross-turn risk dynamics nor scale efficiently without costly manual preference annotation. To close this gap, we introduce \textbf{MINT-Safe}, an open-source visual multi-turn training dataset comprising 11,270 multi-image dialogues and 500 refusal VQA pairs, constructed via multi-agent interaction with text-to-image (T2I) tool-call augmentation. Building on MINT-Safe, we propose \textbf{TAD-Align}, a dialogue safety alignment framework centered on a turn-aware dual-objective reward function. Rather than treating all dialogue turns uniformly, TAD-Align leverages rollout-based safety score variance to dynamically identify turns where the model exhibits inconsistent safety behavior, and adaptively up-weights these turns during optimization. Experiments on Qwen2.5-VL-7B-Instruct and LLaVA-NeXT-7B demonstrate reductions of over 10% in Attack Success Rate (ASR), alongside improvements of at least 8% in harmlessness and 13% in helpfulness on multi-modal multi-turn safety benchmarks, while preserving general model capabilities.

Sign Language Translation (SLT) is a challenging cross-modal task requiring joint modeling of manual articulations and non-manual signals. Existing gloss-free SLT methods effectively capture gestural dynamics but often underutilize facial expressions, which play crucial grammatical and disambiguating roles. This limitation can cause semantic degradation when distinct concepts share similar manual configurations. To address this issue, we propose FEA-SLT (Facial-Expression-Aware Sign Language Translation), a gloss-free end-to-end framework that uses facial dynamics to provide complementary cues to manual signals. FEA-SLT employs a domain-transferred facial encoder to extract expression-sensitive representations and integrates them with manual features through a linguistically motivated Facial-Expression-Aware Fusion (FEAF) module. FEAF captures reciprocal dependencies between manual and facial channels via bidirectional modulation, enhancing syntactic fidelity. Experiments on PHOENIX14T and CSL-Daily show that FEA-SLT achieves state-of-the-art BLEU performance among gloss-free methods, while targeted analyses support improved translation of facial-sensitive utterances. Code is available at https://github.com/TuGuobin/FEA-SLT.

Multimodal large language models (MLLMs) have achieved impressive progress in vision-language reasoning, yet their ability to understand temporally unfolding narratives in videos remains underexplored. True narrative understanding requires grounding who is doing what, when, and where, maintaining coherent entity representations across dynamic visual and temporal contexts. We introduce NarrativeTrack, the first benchmark to evaluate narrative understanding in MLLMs through fine-grained entity-centric reasoning. Unlike existing benchmarks limited to short clips or coarse scene-level semantics, we decompose videos into constituent entities and examine their continuity via a Compositional Reasoning Progression (CRP), a structured evaluation framework that progressively increases narrative complexity across three dimensions: entity existence, entity changes, and entity ambiguity. CRP challenges models to advance from temporal persistence to contextual evolution and fine-grained perceptual reasoning. A fully automated entity-centric pipeline enables scalable extraction of temporally grounded entity representations, providing the foundation for CRP. Evaluations of state-of-the-art MLLMs reveal that models fail to robustly track entities across visual transitions and temporal dynamics, often hallucinating identity under context shifts. Open-source general-purpose MLLMs exhibit strong perceptual grounding but weak temporal coherence, while video-specific MLLMs capture temporal context yet hallucinate entities' contexts. These findings uncover a fundamental trade-off between perceptual grounding and temporal reasoning, indicating that narrative understanding emerges only from their integration. NarrativeTrack provides the first systematic framework to diagnose and advance temporally grounded narrative comprehension in MLLMs.

Socially compliant navigation requires structured reasoning about dynamic pedestrians and physical constraints to ensure safe and interpretable decisions. Vision-language models (VLMs) provide a promising foundation for this task because they can integrate visual observations with language-based social knowledge. However, existing untuned VLMs still struggle to reliably understand fine-grained social norms, making task-specific fine-tuning essential. At the same time, no large-scale egocentric dataset is available this task. To address these challenges, we introduce MUSON, a multimodal dataset for short-horizon social navigation containing 10,110 egocentric samples collected across diverse indoor and outdoor social scenes. MUSON adopts a structured five-step chain-of-thought annotation framework comprising perception, prediction, reasoning, action, and explanation. It explicitly models static physical constraints and employs a standardized six-action decision space. Compared with existing social-navigation datasets, MUSON provides consistent annotations for reasoning, actions, and explanations. We evaluate ten representative small-to-medium VLMs on MUSON. Qwen3-VL-8B achieves the strongest decision-level performance, attaining the highest action accuracy of 0.7765 and Macro-F1 score of 0.7490, as well as the lowest collision rate of 0.0609. These results demonstrate that MUSON is an effective and reusable benchmark for advancing socially compliant navigation. The dataset is publicly available at https://github.com/MUSON-dataset/MUSON/releases/tag/v1.0.

Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertainty, is highly correlated with VLM reliability. While prior entropy-based attacks maximize uncertainty at all decoding steps, implicitly assuming that every token equally contributes to model instability, we reveal that a small fraction (around 20%) of high-entropy tokens, in the evaluated representative open-source VLMs with diverse architectures, concentrates a disproportionate share of adversarial influence during autoregressive generation. We demonstrate that concentrating adversarial perturbations on these high-entropy positions achieves comparable semantic degradation to global methods while optimizing fewer decoding positions. Additionally, across multiple representative VLMs, such attacks induce not only semantic drift but also a substantial unsafe subset (20-31%) under the current pipeline. Remarkably, since such vulnerable high-entropy tokens recur across architecturally diverse VLMs, attacks focused on them exhibit non-trivial transferability. Motivated by these findings, we design a simple Entropy-Guided Attack (EGA) that operationalizes sparse high-entropy targeting and extends it with a reusable token bank, yielding competitive attack success rates (93-95%) with a considerable harmful rate (30.2-38.6%) on the three representative open-source VLMs.

Disclaimer: Samples in this paper may be harmful and cause discomfort. Multimodal large language models (MLLMs) enable multimodal understanding but inherit toxic signals from weakly curated pretraining corpora, leading to explicitly toxic outputs, especially under adversarial triggers that late, opaque training-free detoxification methods struggle to handle. We propose SGM, a white-box neuron-level multimodal intervention that acts like safety glasses for toxic neurons: it recalibrates a set of toxicity-associated neurons via expertise-weighted soft suppression, neutralizing harmful cross-modal activations without any parameter updates. We establish MM-TOXIC-QA, a multimodal toxicity data framework, and compare SGM with existing detoxification techniques. Experiments on open-source MLLMs show that SGM mitigates explicit toxicity in standard and adversarial conditions, cutting average harmful rates from 45.0% to 4.5% while preserving fluency and multimodal reasoning. SGM is extensible, and its combined defenses, denoted as SGM*, integrate with existing detoxification methods for stronger safety performance, providing an interpretable, low-cost solution for toxicity-controlled multimodal generation.

Recent vision-language models (VLMs) like CLIP have shown impressive anomaly detection performance under significant distribution shift by utilizing high-level semantic information through text prompts. However, these models often overlook fine-grained defect cues, e.g., hole, cut, or scratch, that are essential for understanding the anomaly's nature. Moreover, the modality gap between images and text can lead to subtle visual evidence being poorly captured in textual descriptions. To address the gap, we enhance the representation of "abnormal" with structured semantics, bridging coarse anomaly signals and fine-grained defect categories. We propose a hybrid prompting mechanism that combines human-readable descriptions of defect types with learnable token embeddings. Building on these ideas, we introduce DAPO, a Defect-aware Prompt Optimization framework for zero-shot multi-type and binary anomaly detection and segmentation under distribution shift. DAPO aligns anomaly-relevant visual features with their corresponding textual semantics by learning hybrid defect-aware prompts that combine fixed textual anchors with trainable token embeddings. We conducted experiments on public benchmarks (MPDD, VisA, MVTec-AD, MAD, and Real-IAD) and an internal dataset. The results suggest that compared to the baseline models, DAPO achieves a 3.6% average improvement in AUROC and average precision metrics at the image level under distribution shift, and a 5.2% average improvement in AUROC and F1 when localizing novel anomaly types under zero-shot settings.

Vision-language models (VLMs) are increasingly integrated into clinical workflows. However, existing benchmarks primarily assess performance on common anatomical presentations and fail to capture the challenges posed by rare variants. To address this gap, we introduce AdversarialAnatomyBench, the first benchmark comprising naturally occurring rare anatomical variants across diverse imaging modalities and anatomical regions. We call such variants that violate learned priors about "typical" human anatomy natural adversarial anatomy. Benchmarking 25 state-of-the-art VLMs with AdversarialAnatomyBench yielded three key insights. First, when queried with basic medical perception tasks, mean accuracy dropped from 71% on typical to 28% on atypical anatomy. Even the best-performing models, GPT-5, Gemini 2.5 Pro, and Llama 4 Maverick, showed performance drops of 41-51%. Second, model errors closely mirrored expected anatomical biases. Third, neither model scaling nor interventions, including bias-aware prompting and test-time reasoning, resolved these issues. These findings highlight a critical limitation in current VLMs: their poor generalization to rare anatomical presentations. AdversarialAnatomyBench provides a foundation for systematically measuring and mitigating anatomical bias in multimodal medical artificial intelligence (AI) systems.

Vision-Language Models (VLMs) have achieved remarkable progress in integrating visual perception with language understanding. However, effective multimodal reasoning requires both accurate perception and robust reasoning, and weakness in either limits the performance of VLMs. Prior efforts to enhance reasoning often depend on high-quality chain-of-thought (CoT) data, obtained via labor-intensive human annotations, costly proprietary models, or self-training methods that overlook perception. To address these limitations, we propose a simple yet effective self-training framework called See-Think-Learn (STL). At its core, STL introduces a structured reasoning template that encourages the model to see before thinking, first extracting visual attributes in textual form, then using them to guide reasoning. The framework jointly improves perception and reasoning by having the model generate and learn from its own structured rationales in a self-training loop. Furthermore, we augment the training data with negative rationales, i.e. explanations that justify why certain answer choices are incorrect, to enhance the model's ability to distinguish between correct and misleading responses. This fosters more discriminative and robust learning. Experiments across diverse domains show that STL consistently outperforms baselines trained directly only on answers or self-generated reasoning, while qualitative analysis confirms the high quality of its rationales. STL thus provides a cost-effective solution to enhance multimodal reasoning ability of VLMs.

We propose FDRMFL, a task-driven multimodal feature extraction framework for federated regression under non-IID data distributions. Extracting predictive features from high-dimensional multimodal inputs is particularly challenging in this setting: data cannot leave each client, local samples are scarce and heterogeneously distributed, and unsupervised dimensionality reduction discards task-relevant information while federated training introduces representation drift across communication rounds. FDRMFL addresses these challenges through a unified four-term local objective: MSE prediction loss, a correlation-based mutual information surrogate that preserves dependence between the fused representation and the continuous target, a symmetric KL penalty that aligns cross-modal latent distributions before fusion, and an InfoNCE-style contrastive loss that anchors local representations to the global consensus. Experiments on three synthetic and two real-world near-infrared spectroscopy datasets under non-IID federated partitions, with comprehensive ablation and sensitivity analyses, demonstrate that each component contributes to the framework's effectiveness. FDRMFL reduces mean MSE by 33.8% relative to the best traditional baseline (PCA) and by 43.0% relative to VAE in simulation, and attains the lowest overall mean MSE among six federated algorithms including FedAvg, FedProx, MOON, SCAFFOLD, and FedBN.

How does irrelevant information (i.e., distractors) affect test-time scaling in vision-language models (VLMs)? Prior work on text-only language models has shown that textual distractors can intensify inverse scaling, causing models to reason longer but less effective reasoning traces. In this work, we investigate whether similar phenomena arise in multimodal settings. We introduce Idis (Images with distractors), a visual question-answering dataset that systematically varies distractors along semantic and numerical dimensions. Our analyses reveal that visual distractors affect reasoning VLMs in a fundamentally different way from textual distractors: although inverse scaling still emerges, visual distractors reduce accuracy without increasing reasoning length. We further show that attribute counts extracted from reasoning traces provide key insights into how distractors interact with reasoning length and accuracy. As a sanity check, we propose a simple prompting strategy that mitigates distractor-driven predictions in reasoning vision-language models.

The way humans interact with each other, including interpersonal distances, spatial configuration, and motion, varies significantly across different situations. To enable machines to understand such complex, context-dependent behaviors, it is essential to model multiple people in relation to the surrounding scene context. In this paper, we present a novel research problem to model the correlations between two people engaged in a shared interaction involving an object. We refer to this formulation as Human-Human-Object Interactions (HHOIs). To overcome the lack of dedicated datasets for HHOIs, we present a newly captured HHOIs dataset and a method to synthesize HHOI data by leveraging image generative models. As an intermediary, we obtain individual human-object interaction (HOIs) and human-human interaction (HHIs) from the HHOIs, and with these data, we train an text-to-HOI and text-to-HHI model using score-based diffusion model. Finally, we present a unified generative framework that integrates the two individual model, capable of synthesizing complete HHOIs in a single advanced sampling process. Our method extends HHOI generation to multi-human settings, enabling interactions involving more than two individuals. Experimental results show that our method generates realistic HHOIs conditioned on textual descriptions, outperforming previous approaches that focus only on single-human HOIs. Furthermore, we introduce multi-human motion generation involving objects as an application of our framework.

While Multimodal Large Language Models (MLLMs) have become adept at recognizing objects, they often lack the intuitive, human-like understanding of the world's underlying physical and social principles. This high-level vision-grounded semantics, which we term visual knowledge, forms a bridge between perception and reasoning, yet remains an underexplored area in current MLLMs. To systematically evaluate this capability, we present VKnowU, a comprehensive benchmark featuring 1,680 questions in 1,249 videos, covering 8 core types of visual knowledge spanning both world-centric (e.g., intuitive physics) and human-centric (e.g., subjective intentions). Evaluation of 28 SOTA MLLMs reveals that leading models still fall short of human performance, with particularly notable gaps in the world-centric. To bridge this gap, we introduce a new dataset, VKnowQA, and VideoKnow+, a baseline model that explicitly incorporates visual knowledge into MLLMs. VideoKnow+ follows a structured See-Think-Answer paradigm and adopts reinforcement learning with visual knowledge reward, achieving a +3.7% improvement on VKnowU and consistent gains on MVBench (+5.4%), Video-MME (+7.0%), and MMVU (+5.7%). Our work highlights visual knowledge as a missing cornerstone for developing more generalizable MLLMs that can not only see but also truly understand our worlds.

Multimodal large language models (MLLMs) can inadvertently memorize privacy-sensitive information during training. While existing unlearning methods can remove such content, they often severely degrade the model's foundational capabilities, such as general image understanding. This critical shortfall motivates our investigation into benign memory forgetting, the precise removal of targeted, privacy-sensitive knowledge while rigorously preserving unrelated capabilities. To pioneer and evaluate progress toward this objective, we introduce S-MLLMUn Bench, the first benchmark designed to jointly and quantitatively assess an unlearning method's efficacy in knowledge erasure and the preservation of image understanding. Furthermore, we propose the Sculpted Memory Forgetting Adapter (SMFA), a new framework that enables benign memory forgetting. SMFA confines forgetting to designated memory regions, maintaining overall model performance. By initially fine-tuning the model to replace sensitive outputs with refusals, SMFA generates a memory forgetting adapter, followed by a retaining anchor-guided masking mechanism that safeguards unrelated knowledge. Extensive experiments on S-MLLMUn Bench demonstrate that existing methods fail to achieve benign forgetting, whereas our proposed SMFA serves as an effective baseline, successfully achieving targeted knowledge erasure without compromising the model's foundational visual capabilities. Code and data are available at https://github.com/zeng-zhen/S-MLLMUn.

Multimodal survival analysis aims to improve cancer prognosis using heterogeneous biomedical data, such as histopathology images and genomic profiles. A common strategy is to align representations across modalities so that shared signals can be captured. However, strong cross-modal alignment can also remove modality-specific evidence that is critical for survival prediction. In this paper, we revisit multimodal survival learning from a simple observation: effective models should first discover shared patterns across modalities, and then preserve modality-specific signals. This motivates a representation learning principle that we refer to as Together Then Apart. Based on this idea, we propose TTA, a framework that balances cross-modal alignment and representation distinctiveness. TTA first performs prototype-based alignment to capture shared survival-related structures between modalities. It then encourages modality-specific distinctiveness through an anchor-guided contrastive objective. To further account for modality imbalance and noisy correspondences, we model cross-modal interactions using unbalanced optimal transport. We evaluate the proposed approach on multiple TCGA cancer cohorts with paired histopathology and genomic data. TTA consistently improves survival prediction over recent multimodal survival models. Moreover, the learned prototype structures reveal interpretable cross-modal patterns associated with clinical outcomes.

Discrete diffusion-based multimodal large language models (dMLLMs) have emerged as a promising alternative to autoregressive MLLMs thanks to their advantages in parallel decoding and bidirectional context modeling, but most existing dMLLMs incur significant computational overhead during inference due to the full-sequence attention computation in each denoising step. Pioneering studies attempt to resolve this issue from a modality-agnostic perspective via key-value cache optimization or efficient sampling but most of them overlook modality-specific visual token redundancy. In this work, we conduct a comprehensive study on how visual token redundancy evolves with different dMLLM architectures and tasks and how visual token pruning affects dMLLM responses and efficiency. Specifically, our study reveals that visual redundancy emerges only in from-scratch dMLLMs while handling long-answer tasks. In addition, we validate that visual token pruning introduces non-negligible information loss in dMLLMs and only from-scratch dMLLMs can recover the lost information progressively during late denoising steps. Furthermore, our study shows that layer-skipping is promising for accelerating AR-to-diffusion dMLLMs, whereas progressive or late-step pruning is more effective for from-scratch dMLLMs. Overall, this work offers a new perspective on efficiency optimization for dMLLMs, greatly advancing their applicability across various multimodal understanding tasks. The code is available at: https://github.com/Yrdal3910/dMLLM-Visual-Token-Redundancy-Analysis.

Class-Incremental Learning (CIL) aims to continually learn new categories without forgetting previously acquired knowledge. Vision-language models such as CLIP offer strong transferable representations via multi-modal supervision, making them promising for CIL. However, applying CLIP to CIL poses two major challenges: (1) adapting to downstream tasks often requires additional learnable modules, increasing model complexity and susceptibility to forgetting; and (2) while multi-modal representations offer complementary strengths, existing methods have yet to fully realize their potential in effectively integrating visual and textual modalities. To address these issues, we propose BOFA (Bridge-layer Orthogonal Fusion for Adaptation), a novel framework for CIL. BOFA confines all model adaptation exclusively to CLIP's existing cross-modal bridge-layer, thereby adding no extra parameters or inference cost. To prevent forgetting within this layer, it leverages Orthogonal Low-Rank Fusion, a mechanism that constrains parameter updates to a low-rank ``safe subspace" mathematically constructed to be orthogonal to past task features. This ensures stable knowledge accumulation without data replay. Furthermore, BOFA employs a cross-modal hybrid prototype that synergizes stable textual prototypes with visual counterparts derived from our stably adapted bridge-layer, enhancing classification performance. Extensive experiments on standard benchmarks show that BOFA achieves superior accuracy and efficiency compared to existing methods.

Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in addressing patch redundancy and ambiguity, which arise from the inherent information density disparities across modalities. Recently, Multimodal Large Language Models (MLLMs) have emerged as promising solutions to bridge this gap through their robust semantic generation capabilities. However, the dense textual outputs from MLLMs may introduce conflicts with the original sparse captions. Furthermore, accurately quantifying semantic relevance between rich visual patches and concise textual descriptions remains a core challenge. To overcome these limitations, we introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity. Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches. Additionally, it leverages relevance-aware selection with mean value computation to highlight crucial patch-word correspondences, thereby improving cross-modal similarity assessment. Comprehensive experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance, surpassing existing approaches by 23%-86% in rSum across diverse model architectures, with notable enhancements in text-to-image retrieval scenarios. Our implementation is available at https://github.com/Sweet4tars/seps.git.

Graphical user interface (GUI) grounding is a key capability for computer-use agents, mapping natural-language instructions to actionable regions on the screen. Existing Multimodal Large Language Model (MLLM) approaches typically formulate GUI grounding as a text-based coordinate generation task. However, directly generating precise coordinates from visual inputs is challenging and often data-intensive. A more intuitive strategy is to first identify instruction-relevant visual patches and then determine the exact click location within them. Motivated by recent observations that general MLLMs exhibit native grounding ability embedded in their attention maps, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 509k samples (around 101k screenshots), demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 61.5% on ScreenSpot-Pro, 92.1% on ScreenSpot-v2, 68.1% on OSWorld-G, 79.1% on MMBench-GUI-L2, and 60.0% on UI-Vision. Project page: https://github.com/sjz5202/GUI-AIMA .

We introduce MiRAGE, an evaluation framework for retrieval-augmented generation (RAG) from multimodal sources. As audiovisual media becomes a more prevalent source of information online, RAG systems must integrate such media into generation. Yet, existing evaluation methods for RAG are largely text-centric and do not readily transfer to multimodal settings. MiRAGE is a claim-centric approach to multimodal RAG evaluation, consisting of InfoF1, which assesses factuality and information coverage, and CiteF1, which assesses citation support and completeness. We show that, when applied by humans, MiRAGE strongly aligns with extrinsic judgments of output quality. We additionally introduce an automatic implementation of MiRAGE and compare it to multimodal variants of three prominent text-centric RAG metrics---ALCE, ARGUE, and RAGAS---finding that MiRAGE outperforms all three on text while being the only one to generalize to multimodal sources. We release open-source implementations and outline evaluation methods for multimodal RAG.

Existing real-world datasets for multimodal fact-checking have multiple limitations: they contain few instances, cover only one or two languages, focus on a single task, or rely on external news article sets to source true claims. To address these shortcomings, we introduce M4FC, a new real-world dataset comprising 4,982 images paired with 6,980 claims. The images, verified by professional fact-checkers from 22 organizations, represent a diverse range of cultural and geographic contexts. Each claim is available in one or two out of ten languages. M4FC spans six multimodal fact-checking tasks: visual claim extraction, claimant intent prediction, fake image detection, image contextualization, location verification, and verdict prediction. We provide baseline results for all tasks and analyze how combining intermediate tasks affects verdict prediction performance. We make our dataset and code publicly available.

The rapid digitization of histopathology slides has opened new opportunities for computational tools in clinical and research workflows. Content-based slide retrieval can help pathologists identify morphologically and semantically related precedent cases, supporting expert diagnosis and example-based education. Effective retrieval of whole-slide images (WSIs), however, remains challenging because gigapixel slides contain abundant irrelevant content, focal diagnostic patterns and slide-level semantic information that must be represented at a practicable search cost. Here we present PathSearch, a retrieval framework that combines fine-grained attentive mosaics with slide-level embeddings aligned through vision-language contrastive learning. Trained on 6,926 slide-report pairs, PathSearch captures both fine-grained morphological cues and high-level semantic patterns to enable accurate and flexible retrieval. The framework supports two key functionalities: (1) mosaic-based image-to-image (I2I) retrieval, ensuring accurate and efficient slide search; and (2) multimodal retrieval, where text queries can directly retrieve relevant slides. PathSearch was evaluated on eight tasks comprising 5,021 evaluation slides, spanning malignancy assessment on frozen and hematoxylin and eosin (H&E)-stained slides, lymph-node metastasis detection, tumor subtyping, mixed-gallery rare-cancer retrieval, and hepatocellular carcinoma (HCC) risk stratification. Internal and external experimental results demonstrate that PathSearch consistently outperforms the strongest existing methods without compromising multimodal accuracy. A multi-center reader study further demonstrated increases in task-level mean diagnostic accuracy, confidence, and inter-observer agreement with PathSearch's support. Together, these results support the effectiveness of PathSearch across diverse retrieval tasks and evaluation settings.

Recently, remarkable progress has been made in Unified Multimodal Models (UMMs), which integrate vision-language generation and understanding capabilities within a single framework. However, a model's strong visual understanding often fails to transfer to visual generation: it may correctly judge prompt-image alignment while failing to generate a faithful image from the same prompt. This raises a compelling question: Can a model improve itself by using its understanding module to reward its generation module? We introduce SRUM, a self-rewarding post-training framework directly applicable to existing UMMs of various designs. SRUM creates a feedback loop where the model's own understanding module acts as an internal ``evaluator'', providing corrective signals to improve generation without additional human-labeled data or external reward models. To provide comprehensive feedback, SRUM uses a global-local dual reward system: a \textbf{global reward} ensures overall visual semantics and layout, while a \textbf{local reward} refines fine-grained, object-level fidelity. SRUM shows strong generalization, boosting performance on T2I-CompBench from 82.18 to \textbf{88.37} and on T2I-ReasonBench from 43.82 to \textbf{46.75}. Overall, our work establishes a powerful paradigm for enabling a UMM's understanding module to guide and enhance its own generation via self-rewarding.

Unified multimodal models have shown promising results in multimodal content generation and editing but remain largely limited to the image domain. In this work, we present UniVideo, a versatile framework that extends unified modeling to the video domain. UniVideo adopts a dual-stream design, combining a Multimodal Large Language Model (MLLM) for instruction understanding with a Multimodal DiT (MMDiT) for video generation. This design preserves the MLLM's original text generation capabilities, enables accurate interpretation of complex multimodal instructions, and maintains visual consistency in the generated content. Built on this architecture, UniVideo unifies diverse video generation and editing tasks under a single multimodal instruction paradigm and is jointly trained across them. Extensive experiments demonstrate that UniVideo matches or surpasses state-of-the-art task-specific baselines in text/image-to-video generation, in-context video generation and in-context video editing. Notably, the unified design of UniVideo enables two forms of generalization. First, UniVideo supports task composition, such as combining editing with style transfer, by integrating multiple capabilities within a single instruction. Second, even without explicit training on free-form video editing, UniVideo transfers its editing capability from large-scale image editing data to this setting, handling unseen instructions such as changing the environment or altering materials within a video. Beyond these core capabilities, UniVideo also supports visual-prompt-based video generation, where the MLLM interprets visual prompts and guides the MMDiT during synthesis. To foster future research, we released our model and code.

This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text conditions, meanwhile ensuring both modalities are aligned with text. Despite progress in joint audio-video training, two critical challenges still remain unaddressed: (1) a single, shared text caption where the text for video is equal to the text for audio often creates modal interference, confusing the pretrained backbones, and (2) the optimal mechanism for cross-modal feature interaction remains unclear. To address these challenges, we first propose the Hierarchical Visual-Grounded Captioning (HVGC) framework that generates pairs of disentangled captions, a video caption, and an audio caption, eliminating interference at the conditioning stage. Based on HVGC, we further introduce BridgeDiT, a novel dual-tower diffusion transformer, which employs a Dual CrossAttention (DCA) mechanism that acts as a robust ``bridge" to enable a symmetric, bidirectional exchange of information, achieving both semantic and temporal synchronization. Extensive experiments on three benchmark datasets, supported by human evaluations, demonstrate that our method achieves state-of-the-art results on most metrics. Comprehensive ablation studies further validate the effectiveness of our contributions, offering key insights for the future T2SV task. All the codes and checkpoints will be publicly released.

Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as identifying small objects in high-resolution images or detecting key moments in long videos. Existing methods typically rely on complex, task-specific fine-tuning, which reduces generalizability and increases system complexity. In this work, we propose an effective, training-free framework that uses an MLLM's intrinsic uncertainty as proactive guidance. Our core insight is that a model's uncertainty decreases when provided with relevant visual information. We introduce a unified mechanism that scores candidate visual inputs by response uncertainty, enabling the model to autonomously focus on the most informative data. We apply this simple principle to three challenging visual tasks: Visual Search, Long Video Understanding, and Temporal Grounding, allowing off-the-shelf MLLMs to achieve performance competitive with specialized, fine-tuned systems. Our results demonstrate that leveraging intrinsic uncertainty is a powerful strategy for improving fine-grained multimodal performance.

Large Language Models (LLMs) with multimodal capabilities have revolutionized vision-language tasks, but their deployment often requires huge memory and computational resources. Post-training quantization (PTQ) has successfully compressed language models to as low as 1-bit precision, its effectiveness for multimodal LLMs (MLLMs) remains unexplored. In this paper, we present the first method for ultra-low-bit (<4-bit) quantization of MLLMs. Our analysis reveals that multimodal tokens and intermediate layer activations produced by them exhibit significantly higher entropy compared to text tokens, indicating greater functional complexity that makes MLLMs less tolerant to ultra-low bit quantization. However, this entropy varies significantly across layers, with some layers producing lower-entropy activation distributions that we empirically show can better tolerate ultra-low bit quantization. Existing PTQ methods optimize weight quantization within each layer but apply the same target precision uniformly, ignoring this variation in complexity across layers. Building on this insight, we propose LUQ: Layerwise Ultra-Low Bit Quantization, which characterizes each transformer layer's functional complexity via its output activation entropy and selectively applies ultra-low bit quantization to layers encoding simpler, more compressible functions. We also show that multimodal calibration (image and text tokens) boosts VQA performance in the ultra-low bit regime. Evaluated on LLaVA-1.5 and Qwen-2.5-VL across 9 VQA benchmarks, LUQ models use 40% and 31% less memory than their 4-bit counterparts while exhibiting less than 10% degradation on MME.

Lightweight 3D medical image segmentation remains constrained by a fundamental \textit{efficiency / robustness conflict''}, particularly when processing complex anatomical structures and heterogeneous modalities. In this paper, we study how to redesign the framework based on the characteristics of high-dimensional 3D images, and explore data synergy to overcome the fragile representation of lightweight methods. Our approach, VeloxSeg, begins with a deployable and extensible dual-stream CNN-Transformer architecture composed of Paired Window Attention (PWA) and Johnson-Lindenstrauss lemma-guided convolution (JLC). For each 3D image, we invoke a glance-and-focus'' principle, where PWA rapidly retrieves multi-scale information, and JLC ensures robust local feature extraction with minimal parameters, significantly enhancing the model's ability to operate with low computational budget. Followed by an extension of the dual-stream architecture that incorporates modal interaction into the multi-scale image-retrieval process, VeloxSeg efficiently models heterogeneous modalities. Finally, Spatially Decoupled Knowledge Transfer (SDKT) via Gram matrices injects the texture prior extracted by a self-supervised network into the segmentation network, yielding stronger representations than baselines at no extra inference cost. Experimental results on multimodal benchmarks show that VeloxSeg achieves a 26% Dice improvement, alongside increasing GPU throughput by 11$\times$, CPU by 48$\times$, and reducing training peak GPU memory usage by $1/20$, inference by $1/24$. Code is available at https://github.com/JinPLu/VeloxSeg.

Human-AI collaboration often requires dividing complex tasks into complementary subtasks. As a task unfolds, users may want to shift which subtasks they perform and which their AI partner performs, in response to evolving task demands and perceptions of the AI's capabilities. In this work, we investigate whether behavioral signals can reveal such changes during a sequential decision-making task. We conducted a study using hand-and-brain chess, where, on each turn, participants chose either to select the piece type (brain) while their AI partner chose the move (hand), or to choose the move after the AI selected the piece type. Across 21 chess players, this yielded more than 1,100 decisions to retain their role from the previous turn or switch to the other role. Players generally retained their current roles across turns. When participants did switch, they exhibited more exploratory gaze patterns and role switches were associated with lower subsequent move quality. Using these behavioral and task-specific signals, we trained a classifier to distinguish switch from stay decisions, achieving a PR-AUC of 0.56 (compared to a random baseline of 0.39). Feature-set ablations showed that gaze and task-specific features contributed most to model performance. Role switching was not a simple choice between controlling and delegating the task as both roles required participants to perform one subtask and delegate the other. However, interviews showed that many participants perceived selecting the piece type as giving them greater control. Perceived AI ability, relative subtask difficulty, and desired influence over the direction of play shaped these role preferences. These findings suggest that behavioral cues could help intelligent systems recognize when users want to reallocate complementary responsibilities during collaboration.

Personalized object detection aims to adapt a general-purpose detector to recognize user-specific instances from only a few examples. Lightweight models often struggle in this setting due to their weak semantic priors, while large vision-language models (VLMs) offer strong object-level understanding but are too computationally demanding for real-time or on-device applications. We introduce MOCHA (Multi-modal Objects-aware Cross-arcHitecture Alignment), a distillation framework that transfers multimodal region-level knowledge from a frozen VLM teacher into a lightweight vision-only detector. MOCHA extracts fused visual and textual teacher's embeddings and uses them to guide student training through a dual-objective loss that enforces accurate local alignment and global relational consistency across regions. This process enables efficient transfer of semantics without the need for teacher modifications or textual input at inference. MOCHA consistently outperforms prior baselines across four personalized detection benchmarks under strict few-shot regimes, yielding a +10.1 average improvement, with minimal inference cost.

Cardiovascular diseases (CVDs) are the leading cause of death worldwide, accounting for approximately 17.9 million deaths each year. Early detection is critical, creating a demand for accurate and inexpensive pre-screening methods. Deep learning has recently been applied to classify abnormal heart sounds indicative of CVDs using synchronised phonocardiogram (PCG) and electrocardiogram (ECG) signals, as well as multichannel PCG (mPCG). However, state-of-the-art architectures remain underutilised due to the limited availability of synchronised and multichannel datasets. Augmented datasets and pre-trained models provide a pathway to overcome these limitations, enabling transformer-based architectures to be trained effectively. This work combines traditional signal processing with denoising diffusion models, WaveGrad and DiffWave, to create an augmented dataset to fine-tune a Wav2Vec 2.0-based classifier on multimodal and multichannel heart sound datasets. The approach achieves state-of-the-art performance. On the Computing in Cardiology (CinC) 2016 dataset of single channel PCG, accuracy, unweighted average recall (UAR), sensitivity, specificity and Matthew's correlation coefficient (MCC) reach 92.48%, 93.05%, 93.63%, 92.48%, 94.93% and 0.8283, respectively. Using the synchronised PCG and ECG signals of the training-a dataset from CinC, 93.14%, 92.21%, 94.35%, 90.10%, 95.12% and 0.8380 are achieved for accuracy, UAR, sensitivity, specificity and MCC, respectively. Using a wearable vest dataset consisting of mPCG data, the model achieves 77.13% accuracy, 74.25% UAR, 86.47% sensitivity, 62.04% specificity, and 0.5082 MCC. These results demonstrate the effectiveness of transformer-based models for CVD detection when supported by augmented datasets, highlighting their potential to advance multimodal and multichannel heart sound classification.

Unified multimodal models (UMMs) unify visual understanding and generation within a single architecture. However, conventional training relies on image-text pairs (or sequences) whose captions are typically sparse and miss fine-grained visual details, even when they use hundreds of words to describe a simple image. We introduce Reconstruction Alignment (RECA), a resource-efficient post-training method that leverages visual understanding encoder embeddings as dense "text prompts", providing rich supervision without captions. Concretely, RECA conditions a UMM on its own visual understanding embeddings and optimizes it to reconstruct the input image with a self-supervised reconstruction loss, thereby realigning understanding and generation. Despite its simplicity, RECA is broadly applicable: across autoregressive, masked-autoregressive, and diffusion-based UMMs, it consistently improves generation and editing fidelity. With only 27 GPU hours, post-training with RECA substantially improves image generation performance on GenEval (0.73 $\rightarrow$ 0.90) and DPGBench (80.93 $\rightarrow$ 88.15), while also boosting editing benchmarks (ImgEdit 3.38 $\rightarrow$ 3.75, GEdit 6.94 $\rightarrow$ 7.27). Notably, RECA surpasses much larger open-source models and applies broadly across diverse UMM architectures, establishing it as an efficient and general post-training alignment strategy for UMMs.

Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods struggle to separate camouflaged object edges due to model freezing, and (2) MLLM-based methods suffer from poor object separability as large language models merge foreground and background. To address these issues, we propose a novel VCOD method based on SAM and MLLM, called Phantom-Insight. To enhance the separability of object edge details, we represent video sequences with temporal and spatial clues and perform feature fusion via LLM to increase information density. Next, multiple cues are generated through the dynamic foreground visual token scoring module and the prompt network to adaptively guide and fine-tune the SAM model, enabling it to adapt to subtle textures. To enhance the separability of objects and background, we propose a decoupled foreground-background learning strategy. By generating foreground and background cues separately and performing decoupled training, the visual token can effectively integrate foreground and background information independently, enabling SAM to more accurately segment camouflaged objects in the video. Experiments on the MoCA-Mask dataset show that Phantom-Insight achieves state-of-the-art performance across various metrics. Additionally, its ability to detect unseen camouflaged objects on the CAD2016 dataset highlights its strong generalization ability.

Compositional visual reasoning has emerged as a key research frontier in multimodal AI, aiming to endow machines with the human-like ability to decompose visual scenes, ground intermediate concepts, and perform multi-step logical inference. While early surveys focus on monolithic vision-language models or general multimodal reasoning, a dedicated synthesis of the rapidly expanding compositional visual reasoning literature is still missing. We fill this gap with a comprehensive survey spanning 2023 to 2025 that systematically reviews 260+ papers from top venues (CVPR, ICCV, NeurIPS, ICML, ACL, etc.). We first formalize core definitions and describe why compositional approaches offer advantages in cognitive alignment, semantic fidelity, robustness, interpretability, and data efficiency. Next, we trace a five-stage paradigm shift: from prompt-enhanced language-centric pipelines, through tool-enhanced LLMs and tool-enhanced VLMs, to recently minted chain-of-thought reasoning and unified agentic VLMs, highlighting their architectural designs, strengths, and limitations. We then catalog 60+ benchmarks and corresponding metrics that probe compositional visual reasoning along dimensions such as grounding accuracy, chain-of-thought faithfulness, and high-resolution perception. Drawing on these analyses, we distill key insights, identify open challenges (e.g., limitations of LLM-based reasoning, hallucination, a bias toward deductive reasoning, scalable supervision, tool integration, and benchmark limitations), and outline future directions, including world-model integration, human-AI collaborative reasoning, and richer evaluation protocols. By offering a unified taxonomy, historical roadmap, and critical outlook, this survey aims to serve as a foundational reference and inspire the next generation of compositional visual reasoning research.

MultiModal Recommendation (MMR) systems have emerged as a promising solution for improving recommendation quality by leveraging rich item-side modality information, prompting a surge of diverse methods. Despite these advances, existing methods still face two critical limitations. First, they use raw modality features to construct item-item links for enriching the behavior graph, while giving limited attention to balancing collaborative and modality-aware semantics or mitigating modality noise in the process. Second, they use a uniform alignment weight across all entities and also maintain a fixed alignment strength throughout training, limiting the effectiveness of modality-behavior alignment. To address these challenges, we propose EGRA. First, instead of relying on raw modality features, it alleviates sparsity by incorporating into the behavior graph an item-item graph built from representations generated by a pretrained MMR model. This enables the graph to capture both collaborative patterns and modality aware similarities with enhanced robustness against modality noise. Moreover, it introduces a novel bi-level dynamic alignment weighting mechanism to improve modality-behavior representation alignment, which dynamically assigns alignment strength across entities according to their alignment degree, while gradually increasing the overall alignment intensity throughout training. Extensive experiments on five datasets show that EGRA significantly outperforms recent methods, confirming its effectiveness.

Multimodal large language models (MLLMs) have recently demonstrated remarkable reasoning abilities under reinforcement learning (RL) paradigm. However, most existing multimodal medical reasoning models focus on basic reasoning, which refers to shallow inference based on visual feature matching. In contrast, real-world clinical diagnosis extends beyond basic reasoning, demanding complex reasoning that integrates heterogeneous clinical information (such as chief complaints and medical history) with multimodal medical imaging data. To bridge this gap, we introduce MM-Retinal-Reason, an ophthalmic multimodal dataset covering the full spectrum of perception and reasoning. Specifically, it is the first dataset in ophthalmology to encompass both basic and complex reasoning tasks with Chain-of-Thought (CoT) trajectories, aiming to enhance visual-centric reasoning and emulate realistic clinical decision-making. Building upon MM-Retinal-Reason, we propose OphthaReason, the first RL-enhanced ophthalmic multimodal reasoning model with step-by-step reasoning traces. To enable flexible adaptation to both basic and complex reasoning tasks, we further introduce Uncertainty-Aware Dynamic Thinking (UADT), which estimates sample-level uncertainty via entropy and dynamically modulates exploration depth through a shaped advantage mechanism. Comprehensive experiments demonstrate the effectiveness of our model on both basic and complex reasoning tasks, outperforming general-purpose MLLMs, medical MLLMs, RL-based medical MLLMs, and ophthalmic MLLMs by at least 15.47%. Project Page: \href{https://github.com/lxirich/OphthaReason}{link}.

Despite rapid progress in large language models (LLMs), current QA benchmarks still overlook the core challenge of real-world scientific information seeking: synthesizing multimodal evidence scattered across multiple documents and structural formats. Existing QAs remain narrow in scope, relying on unimodal text and short-span reasoning that fail to capture the complexity of real information-seeking. We introduce DocHop-QA, a benchmark of 11,379 instances for evaluating multimodal, multi-document, multi-hop scientific QA. Built from publicly available PubMed articles, DocHop-QA incorporates textual passages, tables, and layout cues, enabling cross-document inference without explicit hyperlinks. To scale realistic QA construction, we develop an LLM-driven generation pipeline grounded in 11 scientific reasoning concepts, producing diverse and coherent question-answer pairs. To highlight the utility and versatility of the dataset, we propose a task-driven evaluation framework spanning four settings, including generative answering, multimodal evidence integration and structured index prediction. Experiments show that current models struggle with DocHop-QA's long-context, multi-evidence demands, establishing it as a rigorous testbed for advancing next-generation scientific QA systems.

Traditional multimodal learning approaches rely on alignment pre-training to bridge vision and language modalities, typically by projecting visual features into discrete text token spaces using large-scale image--text data. We revisit this design choice and propose Inverse-LLaVA, a multimodal architecture that inverts the conventional mapping direction by projecting text embeddings into continuous visual representation space and performing fusion within intermediate transformer layers. This representation-first design enables effective multimodal reasoning without relying on an explicit alignment pretraining stage and significantly reduces dependence on large alignment datasets. Across nine multimodal benchmarks, Inverse-LLaVA demonstrates strong learning efficiency under reduced supervision, achieving substantial gains on reasoning-intensive tasks while exhibiting selective performance drops on perception tasks that depend on explicit visual--text grounding. Our analysis indicates that these trade-offs primarily reflect differences in supervision regime rather than architectural limitations. Together, these results show that alignment pretraining is not strictly required for effective multimodal reasoning and highlight the importance of preserving continuous modality representations, opening a new direction for multimodal architecture design that decouples representation structure from supervision regime for more flexible and efficient multimodal systems.

Multi-view learning is widely applied to real-life datasets, but it often suffers from both missing views and missing labels. Prior probabilistic approaches addressed the missing view problem by using a product-of-experts scheme to aggregate representations from present views and achieved superior performance over deterministic classifiers, using the information bottleneck (IB) principle. However, the IB framework is inherently fully supervised and cannot leverage unlabeled data. In this work, we propose a semi-supervised generative model that utilizes both labeled and unlabeled samples in a unified framework. Our method maximizes the likelihood of unlabeled samples to learn a latent space shared with the IB on labeled data. We also include modality-specific information in likelihood modeling and perform cross-view mutual information maximization in the shared latent space to enhance the extraction of shared information across views. Compared to existing approaches, our model achieves better predictive and generation performance on complex datasets with missing views and limited labeled samples.

AI agents with advanced reasoning and tool-use capabilities have demonstrated impressive performance in web browsing for deep search. However, existing benchmarks such as BrowseComp primarily focus on textual content, overlooking the prevalence of multimodal content. To bridge this gap, we introduce MM-BrowseComp, a novel benchmark comprising 400 challenging, hand-crafted questions designed to evaluate multimodal retrieval and reasoning capabilities. Unlike prior work, MM-BrowseComp incorporates visual prompts and necessitates the extraction of key evidence from web images and videos to complete questions, rendering text-only approaches insufficient. Additionally, we provide a verified checklist for each question, enabling fine-grained analysis of multimodal dependencies and reasoning paths. Our comprehensive evaluation of 27 state-of-the-art models reveals that even leading models like GPT-5-High with tools achieve only 24.25% accuracy, highlighting the suboptimal multimodal browsing capabilities, establishing MM-BrowseComp as a rigorous new standard for the field.

The emergence of audio-visual foundation models underscores the importance of reliably assessing their multi-modal understanding. The VGGSound dataset is commonly used as a benchmark for evaluation audio-visual classification. However, our analysis identifies several limitations of VGGSound, including incomplete labelling, partially overlapping classes, and misaligned modalities. These lead to distorted evaluations of auditory and visual capabilities. To address these limitations, we introduce VGGSounder, a comprehensively re-annotated, multi-label test set that extends VGGSound and is specifically designed to evaluate audio-visual foundation models. VGGSounder features detailed modality annotations, enabling precise analyses of modality-specific performance. Furthermore, we reveal model limitations by analysing performance degradation when adding another input modality with our new modality confusion metric.

Computer-aided medical image analysis is crucial for disease diagnosis and treatment planning. While vision-language models (VLMs) such as CLIP exhibit strong generalization ability, their direct application to medical imaging remains hindered by a substantial domain gap. Existing methods for bridging this gap, including prompt learning and unidirectional modality interaction, typically introduce domain knowledge into only one modality. However, such approaches fail to fully exploit CLIP's inherent dual-modality structure and overlook the synergistic effect of bidirectional cross-modal interaction, resulting in persistent modality misalignment. In this paper, we propose NEARL (iNteracted quEry Adaptation with oRthogonaL Regularization), a novel parameter-efficient VLM framework for bidirectional cross-modal interaction. NEARL consists of two key components: (1) the Unified Synergy Embedding Transformer (USEformer), which dynamically generates compact cross-modal queries to facilitate interaction; and (2) the Orthogonal Cross-Attention Adapter (OCA), which decouples new knowledge into truly novel and incremental components through orthogonal regularization. This design reduces interference from incremental components, enabling more focused learning of novel information and improving modality interaction in VLMs. Notably, NEARL introduces only 1.46M learnable parameters. Extensive experiments on three medical imaging modalities demonstrate state-of-the-art performance (e.g., a 2.3% relative improvement on the pneumonia dataset), along with fast inference and low memory overhead, highlighting its effectiveness for real-world medical vision-language understanding.

Multimodal large-scale models have significantly advanced the development of web agents, enabling perception and interaction with digital environments akin to human cognition. In this paper, we argue that web agents must first acquire sufficient knowledge to effectively engage in cognitive reasoning. Therefore, we decompose a web agent's capabilities into two essential stages: knowledge content learning and cognitive processes. To formalize this, we propose Web-CogKnowledge Framework, categorizing knowledge as Factual, Conceptual, and Procedural. In this framework, knowledge content learning corresponds to the agent's processes of Memorizing and Understanding, which rely on the first two knowledge types, representing the "what" of learning. Conversely, cognitive processes correspond to Exploring, grounded in Procedural knowledge, defining the "how" of reasoning and action. To facilitate knowledge acquisition, we construct the Web-CogDataset, a structured resource curated from 14 real-world websites, designed to systematically instill core knowledge necessary for web agent. This dataset serves as the agent's conceptual grounding-the "nouns" upon which comprehension is built-as well as the basis for learning how to reason and act. Building on this foundation, we operationalize these processes through a novel knowledge-driven Chain-of-Thought (CoT) reasoning framework, developing and training our proposed agent, the Web-CogReasoner. Extensive experimentation reveals its significant superiority over existing models, especially in generalizing to unseen tasks where structured knowledge is decisive. To enable rigorous evaluation, we introduce the Web-CogBench, a comprehensive evaluation suite designed to assess and compare agent performance across the delineated knowledge domains and cognitive capabilities. Our code and data is open sourced at https://github.com/Gnonymous/Web-CogReasoner

The proliferation of Large Language Models (LLMs) in medicine has enabled impressive capabilities, yet a critical gap remains in their ability to perform systematic, transparent, and verifiable reasoning, a cornerstone of clinical practice. This has catalyzed a shift from single-step answer generation to the development of LLMs explicitly designed for medical reasoning. This paper provides the first systematic review of this emerging field. We propose a taxonomy of reasoning enhancement techniques, categorized into training-time strategies (e.g., supervised fine-tuning, reinforcement learning) and test-time mechanisms (e.g., prompt engineering, multi-agent systems). We analyze how these techniques are applied across different data modalities (text, image, code) and in key clinical applications such as diagnosis, education, and treatment planning. Furthermore, we survey the evolution of evaluation benchmarks from simple accuracy metrics to sophisticated assessments of reasoning quality and visual interpretability. Based on an analysis of 60 seminal studies from 2022-2025, we conclude by identifying critical challenges, including the faithfulness-plausibility gap and the need for native multimodal reasoning, and outlining future directions toward building efficient, robust, and sociotechnically responsible medical AI.

Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities. However, further enhancing existing MLLMs necessitates high-quality vision-language datasets with carefully curated task complexities, which are both costly and challenging to scale. Although recent self-improving models that iteratively refine themselves offer a feasible solution, they still suffer from two core challenges: (i) most existing methods augment visual or textual data separately, resulting in discrepancies in data complexity (e.g., over-simplified diagrams paired with redundant textual descriptions); and (ii) the evolution of data and models is also separated, leading to scenarios where models are exposed to tasks with mismatched difficulty levels. To address these issues, we propose C2-Evo, an automatic, closed-loop self-improving framework that jointly evolves both training data and model capabilities. Specifically, given a base dataset and a base model, C2-Evo enhances them by a cross-modal data evolution loop and a data-model evolution loop. The former loop expands the base dataset by generating complex multimodal problems that combine structured textual sub-problems with iteratively specified geometric diagrams, while the latter loop adaptively selects the generated problems based on the performance of the base model, to conduct supervised fine-tuning and reinforcement learning alternately. Consequently, our method continuously refines its model and training data, and consistently obtains considerable performance gains across multiple mathematical reasoning benchmarks. Our code, models, and datasets will be released.