Multimodal

Video misinformation detection is often approached through global multimodal fusion or free-form multimodal reasoning. Both paradigms can under-represent localized authenticity cues that arise from coupled interactions among query phrases, contextual text, and short temporal spans of frames. Because such interactions are inherently higher-order, pairwise graph formulations are insufficient to capture multi-way cross-modal dependencies, whereas hypergraphs offer a suitable representation for these relations. We propose HyperClaim, a discriminative temporal hypergraph framework for sample-level authenticity classification. Using the title or benchmark-provided paired text as a claim-like query, HyperClaim constructs a sparse heterogeneous hypergraph over query tokens, evidence tokens, and sampled frames; applies confidence-aware filtering and source budgeting to form compact text-frame and short-range temporal evidence units; performs adaptive soft-incidence reasoning with residual text-video calibration; and aggregates textual, visual, and hyperedge states through a discrepancy-aware readout. Without relying on generated rationales or external tool calls, HyperClaim preserves fine-grained cross-modal and temporal structure that global fusion tends to flatten. Under the FactGuard temporal protocol, it achieves 83.7%, 82.0%, and 87.3% accuracy on FakeSV, FakeTT, and FakeVV, respectively, outperforming strong discriminative and reasoning-centric baselines. Learned incidence and attention weights further reveal token- and frame-level structure.

Multimodal agents for visual question answering increasingly operate as multi-step trajectories that interleave perception, retrieval, and reasoning, yet evaluation still largely reduces to final-answer accuracy. This aggregate signal cannot tell whether a correct answer was reached through grounded evidence, language priors, or accidental error cancellation. We propose to treat a multimodal agent trajectory as a provenance-constrained state machine: tool outputs are normalized into a Structured Evidence Ledger that serves as the trajectory state, downstream reasoning and decision claims may cite only active ledger entries, grounding is checked at the entity and numeric level, and repair is realized as typed state transitions that cannot introduce content without tool-produced provenance. We instantiate this design as LedgerMind (Provenance-Constrained Multimodal Agentic Reasoning with a Structured Evidence Ledger), augmented by a Three-Layer Grounding Protocol, an Adaptive Dual-Path Dispatcher that matches reasoning depth to question complexity, and an Event-Triggered Verification-and-Repair engine with a formal provenance non-amplification guarantee. We use LedgerMind to target four recurring failure patterns that final-answer accuracy tends to obscure: unsupported intermediate reasoning, citation-backed entity hallucination (Phantom Grounding), over-reasoning on simple queries, and repair-time amplification. Experiments across multiple multimodal reasoning benchmarks and backbone MLLMs show that LedgerMind improves both answer accuracy and trajectory-level faithfulness.

On-policy distillation provides dense supervision for multimodal reasoners, but its trajectory-level reward cannot determine whether a failed answer arose from perception or subsequent reasoning. Perception Success Rate (PSR), estimated from multiple reasonings sharing one perception, remains ambiguous because low success conflates perceptual insufficiency with reasoning difficulty. We introduce \textbf{Perception-Correction Distillation (PCD)}, a label-free method that identifies correctable perception failures using downstream failure and teacher--student disagreement as complementary witnesses. Their product, , forms a soft AND gate that strengthens distillation only when both witnesses are present. We motivate this rule through Bayesian evidence combination and show that multiplication is the unique normalized bilinear gate that vanishes when either witness is absent. PCD uses separated perception--reasoning rollouts and mean-preserving weights, leaving the reasoning objective unchanged. Across eight benchmarks, PCD improves the 8B 2B macro average from 44.50 with OPD to 47.28 and the 32B 8B result from 56.94 to 61.22. In matched 2B ablations, removing PCD and separated rollout reduces held-out average by 2.22 and 0.88 points, respectively. Effective multimodal distillation therefore depends not only on what the teacher predicts, but also on identifying when perception is the appropriate target of correction.

Multimodal large language models (MLLMs) are increasingly used to analyze pathology images. However, dominant multimodal benchmarks in pathology mainly score final diagnostic answers, captions, or reports. These evaluations provide limited insight into whether a model understands the multiscale visual content needed for pathology reasoning and decision-making. We introduce PathVU, a vision-anchored benchmark for fine-grained and multiscale visual understanding in computational pathology. Built from 23 public pathology imaging datasets with human-supervised labels and spatial annotations, PathVU evaluates MLLM understanding in two fields of view: Region FOV for high-resolution local regions and Slide FOV for macro whole-slide views. By converting raw annotations into deterministic task targets, PathVU enables programmatic scoring of region localization, visual recognition, quantity estimation, spatial reasoning, and insufficient-context judgment. The benchmark contains 14 VQA-style tasks, 61,673 images, and 308,070 samples across 28 organs and 7,253,526 annotations. Evaluating 18 representative general-purpose, medical-domain, and pathology-oriented MLLMs, we observe substantial limitations even in advanced models on fine-grained visual tasks across multiscale pathology images. PathVU provides a reproducible basis for developing and evaluating pathology MLLMs with explicit multiscale visual understanding.

Agentic vision-language models (VLMs), which interleave textual reasoning with explicit tool calls such as cropping and code-based image manipulation, have emerged as a compelling paradigm for reliable and interpretable multimodal reasoning. However, recent studies have revealed that such models often use tools unfaithfully. Many process images are irrelevant to the question (e.g., the tool crops the wrong region or misses the queried target), yet the call still receives full credit and the model still answers correctly. Such decorative or misaligned tool calls waste computation and reveal that the model leans on prior knowledge or the original image rather than the evidence it retrieves. This may stem from two limitations of prevailing methods: the tool reward fails to distinguish useful from useless calls, and tool feedback carries no signal of usefulness. To this end, we introduce FaithEyes, a multi-agent self-judging framework. Concretely, we use a VLM to judge whether each process image helps answer the question. The judgement is injected into the reasoning context as part of the tool observation to help subsequent reasoning, and meanwhile is used to scale the tool reward by the helpful-tool ratio to suppress reward hacking. To keep judgement available at evaluation and thus ensure train-test consistency, we further design a multi-agent framework where the model itself serves as a subagent to judge the tool calls from main agent, eliminating any dependence on an external model at inference. Training via a two-stage SFT + RL pipeline on adapted open-source data, FaithEyes attains competitive or superior accuracy across visual perception and reasoning benchmarks, while markedly improving tool faithfulness. The homepage is at https://github.com/Mosi-AI/FaithEyes.

While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- erage and contextual understanding. Recently, commercial multimodal moderation APIs built on large foundation models have been introduced with the promise of providing broader and more capable safety filters. In this work, we analyze whether this shift also yields more robust image moderation. We conduct a large-scale black-box evaluation on three established commercial image-moderation services and compare their robustness. By evaluating seven simple, model-agnostic image transformations across multiple providers, datasets, harm categories, perceptual-similarity constraints, and transformation intensities, we find that: (1) all three commercial services can be bypassed using inexpensive image transformations that require no gradients, surrogate models, or knowledge of the target system; (2) even fixed transformations such as color inversion and grayscale conversion induce unsafe-to-safe decision changes while preserving content that remains recognizable to humans; (3) their robustness varies substantially across datasets and harm categories, with multimodal content and self-harm exhibiting pronounced vulnerabilities. This yields the conclusion that replacing conventional moderation classifiers with foundation-model-based APIs does not, by itself, provide a reliable security boundary. Such systems must be evaluated under realistic transformations and deployed as one component of a layered moderation pipeline rather than as standalone safety filters.

Existing multimodal long-term memory agents use external memory to overcome the limited context available for long videos. However, most methods emphasize what to store rather than how stored memory should be retrieved. When retrieval becomes inaccurate or repeatedly fails to obtain useful evidence, existing agents lack mechanisms to diagnose failures from previous task trajectories and adapt future search strategies.We introduce Reflective Retrieval Memory (RRM), a reflective memory framework for long-horizon multimodal reasoning. RRM augments an entity-centric multimodal memory graph with reflective experience memory, which distills transferable procedural retrieval knowledge from historical task trajectories. Unlike episodic and semantic memories that preserve factual evidence from the current video, reflective experience memory captures reusable search strategies across tasks. RRM converts retrieved experiences into query-level guidance, while answer generation remains conditioned only on factual evidence newly retrieved from the current video. A lifecycle management mechanism further regulates experience memory through usage frequency, reuse feedback, and temporal decay, thereby reducing redundancy and noise. RRM consistently outperforms previous state-of-the-art approaches on M3-Bench-Robot, M3-Bench-Web, and Video-MME-Long, demonstrating the effectiveness of reflective retrieval memory for long-horizon multimodal reasoning.

Interleaved multimodal Chain-of-Thought (CoT) improves visual reasoning by incorporating auxiliary visual evidence into intermediate reasoning. However, existing approaches remain constrained by externally defined reasoning traces and visual operations, limiting their ability to develop flexible and abstract visual thinking. Reasoning with latent has recently offered a promising direction by internalizing intermediate computation into continuous representations. Nevertheless, existing visual-latent methods mainly supervise latent states through alignment with compressed auxiliary visual features, treating them as proxies for visual observations rather than active reasoning states. Consequently, they capture the provided evidence but fail to fully internalize the abstract reasoning process induced by multimodal CoT. In this paper, we propose OPLD (On-Policy Latent Distillation), a simple framework that transfers the reasoning capability induced by privileged multimodal CoT into latent reasoning representations. Extensive experiments on diverse multimodal benchmarks demonstrate that OPLD consistently outperforms existing latent reasoning methods and achieves state-of-the-art performance on multiple benchmarks. The results suggest that supervising latent representations at the reasoning-process level provides a more effective paradigm for multimodal latent reasoning than conventional feature-level alignment.

Face-and-voice association learning is one of the most challenging tasks in deep learning. In this paper, we propose a simple but powerful cross-modal feature embedding method for the association of faces and voices. Previous work has studied cross-modal association tasks to establish the correlation between voice clips and facial images. These works have addressed cross-modal discrimination but underestimate the importance of handling heterogeneity in inter-modal features between audio and video, resulting in a lot of false positives and false negatives. To tackle the problem, the proposed method learns the embeddings of cross-modal features by making another feature exist between cross-modal features, facilitating the voice and face features of the same person to be embedded in a convex hull. Moreover, the incorporation of cross-modal attention mechanisms with convex embedding techniques represents a highly effective strategy for the attenuation of false positives and false negatives, accomplished via the minimization of inter-class discrepancies. We exhaustively evaluated our method for cross-modal verification, matching, and retrieval tasks on the large-scale VoxCeleb dataset. Extensive experimental results demonstrate that the proposed method achieves notable improvements over existing state-of-the-art methods.

Automating industrial CAD design and manufacturing places distinctive demands on multimodal foundation models: the model must see engineering drawings and 3D geometry screenshots, write correct parametric-modelling scripts and Windows COM API code, and cover the full range from single parts to assemblies. General-purpose multimodal models fall short on these tasks, while single-task fine-tuning is too narrow to support the diverse calls that upper-layer agents issue. We build IndustryForge-27B on top of Qwen3.5-VL-27B by curating and integrating six industrial-CAD sub-corpora totalling $\sim$52k multimodal samples---CAD Visual QA (CAD-VQA), parametric CAD code (text2cadquery), assembly-level CAD code (text2cadquery-assembly), and three COM sub-corpora for Inventor / SolidWorks (com_2d / com_3d / com_assembly)---and training with a unified multi-task SFT recipe. Across four CAD-domain benchmarks IndustryForge-27B lifts the base model by $+33.65$~pp on average and outperforms the strong closed-source model GPT-5.4 on all four; across eleven general-capability benchmarks it retains, and slightly improves upon, the base model ($+1.56$~pp mean, no catastrophic forgetting). IndustryForge-27B will serve as the common substrate for downstream industrial-agent projects, providing a unified starting point for a full-stack industrial agent that spans from CAD design to industrial-software operation, from parts to assemblies, and from single-shot generation to closed-loop self-improvement.

Multimodal long documents are core carriers of professional knowledge, where critical evidence is sparsely distributed across paragraphs and modalities. This easily causes key information omission and cross-modal hallucinations in summarization by multimodal LLMs. These issues stem from attention drift in long-range dependency modeling and gaps in inter-modal alignment. To address this, we introduce MMLDSum-Bench, a high-quality benchmark for multimodal long-document summarization, covering multiple domains, context-length scales, and visual-textual modality distributions. We further propose MMLDSum-LLM, a reproducible two-stage training framework that combines supervised fine-tuning with visual-alignment weighted loss and keyword-aware weighted loss, followed by GRPO with a multi-objective reward (keyword coverage, image-text alignment, ROUGE, and length control). Extensive experiments on MMLDSum-Bench, comparing against leading closed-source and open-source multimodal models under a unified evaluation protocol - including LLM-as-a-judge scoring, atomic-claim precision/recall, image-text alignment (ITA), and ROUGE - demonstrate that our approach significantly improves key-information coverage and cross-modal consistency.

Due to their strong generalizable multimodal processing and reasoning capabilities, Multimodal Large Language Models (MLLMs) have demonstrated significant potential as universal image retrievers, effectively addressing diverse real-world image retrieval tasks. Nevertheless, pioneering studies, while promising, overlook the potential of fine-grained context modeling and disentangled fine-tuning objectives in enhancing MLLMs' retrieval performance, particularly for complex tasks such as long-text-to-image retrieval, visual dialog retrieval, and composed image retrieval (CIR). Therefore, in this work, we propose an automated fine-grained multimodal quintuple dataset construction pipeline and a novel two-stage fine-grained multimodal fine-tuning strategy. The dataset generation pipeline produces a comprehensive CIR dataset with fine-grained image captions and modification text, facilitating fine-grained context modeling. Beyond the previously entangled fine-tuning paradigm, our approach separates the fine-tuning process into two distinct stages: (1) fine-grained context reasoning-oriented fine-tuning and (2) fine-grained retrieval-oriented fine-tuning. These stages aim to sequentially enhance the model's context understanding and query-target alignment capabilities, thereby improving retrieval performance. Extensive experiments across five datasets encompassing diverse and complex image retrieval tasks demonstrate the remarkable superiority of our method over existing approaches in zero-shot retrieval settings, even with a more lightweight MLLM backbone compared to those methods.

As large vision-language models (LVLMs) are deployed globally, the combination of multilingual instructions and visual information makes malicious attacks more covert and sophisticated than ever before. However, existing methods isolate language and modality defenses, which, coupled with the scarcity of safety data and high fine-tuning costs, makes it difficult for models to defend against compound attacks. To address this severe challenge, we propose a neuron-level cross-dimensional safety alignment framework driven by modality- and language-shared safety neurons (MLS-Neurons). First, we identify monolingual and unimodal safety neurons by comparing responses to harmful and benign samples, quantifying functional saliency through activation strength and downstream impact. Then, by intersecting these unimodal neurons within each language, we extract modality-shared safety neurons (MS-Neurons) responsive to both visual and textual risks, bridging the safety representation gap between modalities. Furthermore, using English as a semantic anchor, we intersect MS-Neurons across languages to identify modality- and language-shared safety neurons (MLS-Neurons), serving as key defenses against compound attacks. Finally, we update only this minimal subset of shared neurons (~0.03% of parameters), transferring English-only safety supervision to multilingual and multimodal scenarios. Extensive experiments show that our method significantly outperforms state-of-the-art approaches across diverse multilingual and multimodal safety benchmarks while preserving general utility.

Scene text spotting requires high-precision alignment between textual recognition and spatial localization. While visual-token grounding has emerged as a promising formulation for Multimodal Large Language Models (MLLMs), the previous multi-patch paradigm often introduces redundant noise and localization ambiguity, particularly for dense or small text instances. To address this, we propose Single-Patch Text Spotting (SPaTS), a vision-centric framework that routes each text instance through a single anchor visual token and then recovers geometry via full-image refinement. To accurately identify this anchor without oracle labels, we introduce Single-Patch Selective Optimization (SPaSO), a reinforcement learning framework that optimizes discrete visual-token selection using patch-level rewards. To further improve representation robustness and localization precision, we introduce Directional Embedding Alignment (DEA) to suppress unstable norm bias by decoupling feature magnitude and direction, and Patch-Enhanced Decoding (PED) to fuse the routed anchor with language semantics and cross-attend over the full-image feature map for geometry-aware boundary regression beyond coordinate-space surrogates. Extensive experiments demonstrate that SPaTS consistently and significantly outperforms both frontier closed-source MLLMs and OCR MLLMs. Code is available at https://github.com/eeNickTang/SPaTS.

Mental health understanding in long-form videos requires nuanced reasoning over observable behavior, interpersonal context, and latent psychological states. Existing benchmarks largely reduce this task to coarse-grained classification, providing limited insight into whether models truly understand psychological phenomena or rely on superficial correlations. To address this limitation, we introduce MMHBench, a comprehensive multimodal benchmark for multi-perspective mental health understanding, comprising 268 long-form videos and 2,184 carefully curated questions. MMHBench organizes the evaluation into two complementary settings: (1) third-person assessment, consisting of 605 questions that focus on the interpretation of observable behaviors and multimodal evidence, and (2) first-person perspective-taking, comprising 1,579 questions that require perspective-conditioned reasoning to identify the interpretation of the mental state supported by the available multimodal evidence. We propose a Multi-Agent Question Generation (MAQG) framework that simulates diverse social roles to synthesize questions from multiple perspectives. The generated questions are refined through multi-role feedback and iterative optimization, followed by expert-guided verification to ensure quality and validity. Extensive evaluation of 22 representative multimodal large language models (MLLMs), spanning both open-source and leading closed-source models, demonstrates that long-form video mental health understanding remains highly challenging.

Camouflaged Object Detection (COD) aims to identify and segment camouflaged objects in complex environments, which are often concealed because their color and texture are similar to the background. Several existing COD methods introduce depth maps to boost detection performance via learning complementary RGB-D features, ignoring modality-specific characteristics of concealed objects in the depth domain. To address this issue, we propose a depth collaborative network, called VCP-DCN, to mine distinguishable multi-modality features beyond visual concealed prototype in depth domain. Specifically, VCP-DCN progressively performs multi-modality alignment, interaction, and fusion for the COD task. In the \textbf{alignment} stage, we propose a Separable Prototype Embedding (SPE) module to learn modality-consistency and modality-specific RGB/depth prototype tokens through prototype contrastive learning. Furthermore, we develop a Multi-modality Dual Attention (MDA) module to enhance the cross-modal feature representation through local response maps between modality-consistency RGB/depth prototype tokens and visual tokens on the \textbf{interaction} stage. Finally, we design a Depth Adaptive Injection (DAI) module to adaptively measure contribution of RGB/depth features with a decision-making mechanism, which calculates similarity distance between RGB/depth modality-specific prototype tokens and modality-consistency ones on the \textbf{fusion} stage. Extensive experiments demonstrate the effectiveness of our VCP-DCN on three authoritative datasets.

In recent years, multi-view clustering has attracted widespread research interest. However, due to limitations in data collection devices, data across different views often suffer from misalignment, leading to the partial view alignment problem (PVAP). To mitigate the impact of view asymmetry and irrelevant samples, this paper proposes a framework for partial multi-view clustering via dual alignment and structure enhancement (DAS-PMVC), which leverages view structure consistency and semantic relevance. Specifically, DAS-PMVC includes three parts: \textbf{anchor graph structure alignment}, where sample joint embedding representations with consistent latent space are derived from anchor point relationships for initial view alignment; \textbf{structure-enhanced feature learning}, where the model learns view structure information through pretraining and combines multi-view graph convolutional networks to further extract deep latent features from the aligned graph structure to improve the discriminative power of representations; and \textbf{a dual alignment strategy}, where initial alignment is performed through the anchor graph in the pretraining phase, and contrastive learning loss and the Hungarian algorithm are introduced in the training phase to further optimize the alignment of latent features. Experimental results on various datasets demonstrate that the DAS-PMVC framework outperforms existing state-of-the-art methods in clustering performance, showcasing its effectiveness and superiority.

Reliable deployment of multimodal large language models (MLLMs) requires deciding whether a confident visual answer should be trusted, reviewed, or routed to a stronger system. Confidence scores capture candidate margins, but not where the estimated signed visual readouts associated with those margins come from or how they are distributed. We study inference-time risk detection for closed visual answers using the same white-box prefill path that produces the answer. Witness Evidence Portfolios (WEP) first estimates, layer by layer, which visual contributions support or contradict the predicted candidate. It summarizes these contributions through two interpretable route families: question-related evidence provenance and signed evidence concentration. Nested grouped validation chooses the more reliable family and a sparse top-k route portfolio, which is fused with candidate confidence. WEP needs no image perturbation, decoding change, backward pass, or external verifier. Across three MLLMs and four binary-answer benchmarks, WEP improves mean error AP by 0.134. All 12 model--dataset gains are positive, and image-cluster bootstrap intervals are strictly positive on 10 pairs. WEP targets white-box closed-answer systems and uses a labeled calibration slice.

Federated graph learning enables collaborative training over decentralized graph data without sharing raw graph information. As such risks evolve, clients must learn emerging classes from private multimodal graph streams, retain historical categories, and reject samples outside the known class space. In this setting, clients must learn emerging classes from private multimodal graph streams while preserving historical categories and rejecting samples outside the current known class space. The core challenge is catastrophic forgetting, which in federated multimodal graphs is not merely a classifier-level failure: old knowledge can be erased through modality-semantic overwriting, topology-induced structural erosion, and federated memory fragmentation. To address this challenge, we propose \textbf{FedOGL}, a semantic-structural memory preservation framework. On the client side, FedOGL preserves historical decision behavior through replay and task-start distillation, while protecting graph-propagation memory via projection onto a globally shared structure basis. On the server side, FedOGL maintains and transfers compact category prototypes to facilitate cross-client knowledge sharing without exposing raw graph data. Extensive experiments demonstrate that, compared with the best-performing baselines, FedOGL reduces performance degradation caused by catastrophic forgetting by \textbf{42.67%}, while maintaining or improving performance on downstream tasks.

Multimodal Large Language Models (MLLMs) have achieved strong performance on a wide range of vision-language tasks, but often fail under imperfect or shifted contexts. A reliable MLLM should refuse truly out-of-context (OOC) questions with subject-level context shifts while still answering shifted in-context (Shifted IC) questions with non-subject context shifts. Existing benchmarks mainly target OOC or visually unanswerable questions, but overlook answerable Shifted IC cases and cover limited OOC shifts. To fill this gap, we present MMOOC, a large-scale benchmark for evaluating refusal and robust answering abilities of MLLMs. MMOOC contains over 41K image-question pairs, including answerable Shifted IC cases and unanswerable OOC cases, spanning three question formats, eight shift types and six visual scenarios, with data quality ensured through MLLM-based filtering and human verification. We evaluate model responses using Accuracy and Refusal Rate, and further introduce an LLM-as-a-Judge metric to assess the correctness of model reasoning. Experiments on diverse MLLMs show that current models still struggle to balance answer-ability and refusal under shifted contexts. We further analyze key failure patterns and show that post-training can improve robustness. MMOOC will be made publicly available.

Hateful memes are a growing form of multimodal online harm, where hostile intent is often conveyed through the joint interpretation of images, text, cultural references, and implicit targets. While hateful meme detection has advanced in high-resource languages, Arabic remains underexplored, with existing meme resources focusing mainly on propaganda or coarse harmful-content labels. We introduce AHA-Memes (Arabic HAteful Memes), which is, to our knowledge, the first large-scale Arabic hateful meme benchmark with fine-grained, multi-label annotations. The dataset includes 5K manually annotated memes using a taxonomy that captures hate types, i.e., attack strategies. We further provide ~66K silver-labeled memes to support future studies. We benchmark text-only, image-only, and late-fusion multimodal models, as well as few-shot in-context learning (ICL) and open- and closed-weight Vision-Language Models (VLMs) under zero-shot and fine-tuning settings. Our results establish strong baselines and highlight key challenges in culturally grounded Arabic hateful meme detection. We release the dataset, annotation guidelines, and evaluation scripts to support future research. WARNING: This paper contains examples that may be disturbing to readers.

As Multimodal Large Language Models (MLLMs) are increasingly deployed in decision-critical pipelines such as robotics, embodied AI, and safety monitoring, the opacity of their spatial judgments limits operator trust and auditability. MLLMs demonstrate strong reasoning but often struggle with fine-grained spatial understanding and object hallucination. Prior work, ByDeWay, introduced Layered-Depth-Based Prompting (LDP), a training-free framework that mitigates hallucinations by structuring prompts using monocular depth estimation. However, coarse depth layering falls short in resolving object-to-object spatial relationships within the same geometric plane, such as projective ("left of", "above") and topological ("inside", "touching") relations. We propose ByDeWay-V2, which integrates explicit spatial relational context alongside depth cues, expressed as human-readable predicates that serve as auditable evidence for downstream decision support. Using an open-vocabulary object detector (YOLO-World-L), our framework computes pairwise geometric relations between detected objects and injects them as structured spatial predicates into the MLLM prompt, bridging 3D scene depth and 2D spatial semantics without any training. We evaluate ByDeWay-V2 on the Visual Spatial Reasoning (VSR) and BLINK benchmarks across multiple MLLMs, with hallucination grounding assessed via POPE. On the BLINK spatial subset, ByDeWay-V2 achieves a 46 percent relative F1 improvement over LDP for Qwen2.5-VL, and recovers BLIP-Base's spatial reasoning on VSR from near-random performance to a competitive F1 of 0.53. Our lightest configuration operates under a strict 40-token context budget on CPU, showing the framework's suitability for resource-constrained, real-time decision-support settings.

The promise of multimodal fusion lies in combining complementary sources of evidence, yet more evidence does not always yield a better prediction. Recent multimodal models have advanced fusion through richer cross-modal interaction and sample-adaptive fusion. However, the influence assigned to a modality during fusion does not reveal whether that source is unreliable, redundant, or poorly matched to a specialized expert. To address this limitation, we introduce TIER-MoE, a risk-guided subspace mixture-of-experts model that defines sample-specific modality reliability as the prediction loss its unimodal predictor is expected to incur. This risk is learned from out-of-fold predictions generated by models that were not trained on the corresponding sample. TIER-MoE combines the estimated risk with expert-specific subspace compatibility for sparse modality-expert routing, while an always-active shared path preserves multimodal complementarity. We evaluate TIER-MoE on four public multimodal biomedical datasets spanning Alzheimer's disease status, skin-lesion malignancy, and retinal classification. Results demonstrate its superiority over state-of-the-art methods in predictive performance and probability calibration, with consistent improvements in Macro-F1 and Brier score and strong zero-shot generalization to an external cohort.

Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cross-modal understanding. In Multimodal Continual Instruction Tuning (MCIT), however, shifting visual distributions and evolving instruction semantics cause this shared projector to drift, leading to projector-level forgetting, an issue largely overlooked by methods that focus primarily on the LLM backbone. We introduce Progressive Multimodal Alignment (PMA), a framework that enables the projector to adapt continually while preserving previously learned alignment. PMA detects multimodal distribution shifts via a lightweight representation descriptor and progressively expands projector experts only when needed. An expandable router integrates expert outputs based on multimodal features, while the original pretrained projector is retained as a stable alignment anchor. This progressive mechanism balances stability and plasticity with sub-linear parameter growth and serves as a method-agnostic add-on to existing MCIT approaches. Extensive experiments on two recent MCIT benchmarks demonstrate that mitigating projector-level forgetting yields consistent gains over prior state-of-the-art methods when combined with PMA. Moreover, PMA scales across diverse MLLM backbones, demonstrating robust and broadly applicable MCIT performance.

Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text. While existing explainability methods identify influential image regions or text tokens, they cannot answer a fundamental question: which modality drives a prediction? Consequently, a model may produce the correct output while relying on the wrong source of evidence, masking shortcut learning and unsafe reasoning. We formulate modality attribution as a complementary explainability objective for multimodal foundation models and propose Counterfactual Modality Attribution (CMA), the first framework for quantifying modality-level contributions in MLLMs. CMA generates image-only, text-only, and joint multimodal counterfactuals using coupled diffusion priors and converts them into principled modality attribution scores through a cooperative game-theoretic formulation based on Shapley values. We evaluate CMA on controlled synthetic benchmarks with known ground-truth modality reliance and on a real-world multimodal clinical dataset. CMA correctly identifies the decision-driving modality in 98% of controlled cases and consistently outperforms baselines, revealing failures of cross-modal reasoning that remain invisible to predictive accuracy alone. Our results establish modality attribution as a complementary dimension of explainability beyond feature attribution, providing a principled framework for auditing multimodal foundation models in safety-critical applications.

Vision-language pre-training (VLP) serves as a cornerstone for medical multimodal representation learning. However, existing medical VLP frameworks are often constrained by the limited context windows and shallow representational capacities of lightweight text encoders when processing lengthy, terminology-dense clinical reports. While integrating medical large language models (LLMs) offers unprecedented clinical reasoning capabilities, it introduces three major bottlenecks: (i) the anisotropic representational collapse of generative LLMs under standard contrastive objectives, (ii) the prohibitive memory overhead of joint end-to-end training with large batch sizes, and (iii) the medical hallucinations induced by vanilla contrastive losses that ignore fine-grained anatomical laterality and negation modifiers. To address these challenges, we propose \textbf{SCALPEL}, a \textbf{S}emantic \textbf{C}ross-modal \textbf{A}lignment framework via \textbf{L}LM-\textbf{P}owered \textbf{E}ncoder \textbf{L}earning. First, Clinical Report Contrastive fine-tuning converts a generative LLM into an isotropic encoder via domain-specific clinical text adaptation. Second, an asymmetric alignment strategy leverages offline feature caching to enable efficient training. Critically, we formulate an Anatomy-Negation Aware Objective that explicitly penalizes mismatched image-text pairs involving laterality confusion or false negations. Extensive experiments across MIMIC-CXR, CheXpert, and IU X-Ray benchmarks demonstrate that SCALPEL achieves state-of-the-art performance in cross-modal retrieval, zero-shot disease classification and medical visual question answering.

Audio-video generative models achieve impressive quality but suffer from high latency, making them unsuitable for real-time applications. Although several streaming audio-video generation methods have been proposed, they remain costly and fail to support long-form generation. To address this, we propose \textbf{Ripple}, a real-time joint audio-video generation system with a cross-modal recurrent memory mechanism. To enable efficient streaming inference while preserving long-term context, Ripple combines a fixed-length sliding-window attention with modality-specific memory states that continuously summarize audio and video context. Cross-modal memory interaction is further introduced to enhance audio-visual synchronization. To learn this memory-augmented model effectively, we devise a three-stage training recipe: (1) adapting a bidirectional audio-video teacher to block-wise causal attention with simulated memory, (2) optimizing the memory construction and interaction pipeline through end-to-end distillation, and (3) applying online reinforcement post-training tailored for streaming audio-video generation. As a result, Ripple achieves ~28 FPS at 480P resolution, over faster than the teacher, while capable of coherent long-form generation. Extensive experiments on both short-video and long-video benchmarks demonstrate our superior performance over existing offline and online joint audio-video generation methods.

Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvements in aggregate performance do not reveal what a smaller model actually inherits. Existing studies are largely designed and evaluated on limited task sets or aggregate metrics; as evaluation expands to broader task collections, whether different capabilities can transfer across scales remains poorly understood. To investigate this question, we introduce Cross-Scale Directional Parameter Injection (CDPI), a simple linear probe to analyze cross-scale knowledge transfer during heterogeneous fusion. A local theoretical analysis indicates that knowledge transfer selectivity is determined at first order by capability-dependent responses to a shared injection direction, while second-order curvature effects constrain the effective transfer regime. Across four Qwen3-VL model pairs and twelve multimodal benchmarks, our experiments reveal a consistent pattern of selectivity: gains concentrate on reasoning, particularly high-level reasoning, whereas perception performance remains close to that of the original target model. Component-wise ablations further show that high-level reasoning gains arise primarily from the language model, while ratio analysis finds that positive selective transfer occurs mainly in the small-ratio regime. These findings recast cross-scale heterogeneous MLLM fusion as selective language-side reasoning transfer within a narrow, low-interference regime, rather than broad capability inheritance.

3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing demand for reliable quality assessment. Unlike conventional image quality assessment (IQA), the quality of a 3DGS scene depends not only on the perceptual fidelity of rendered views, but also on scene-level factors such as spatial structure and cross-view consistency. Existing IQA methods are limited by their reliance on 2D perceptual cues, whereas general multimodal large language models (MLLMs) are not designed for stable quality regression and may produce unreliable judgments. To address these limitations, a multimodal quality assessment framework is developed for 3DGS scene understanding. First, a 3D-aware quality representation learning framework is introduced by augmenting a VGGT-based encoder with a dedicated quality head. Multi-view images are encoded into view-specific features and aggregated to capture cross-view consistency, while geometric cues are incorporated through joint modeling of depth and point-cloud-related structural information, enabling the learning of structure-aware quality representations beyond appearance-driven features. Second, a grounded multimodal reasoning mechanism is constructed by jointly feeding original images, depth maps, point cloud renderings, and camera parameters into a Qwen-based MLLM.

Humanoid robots increasingly require multi-modal understanding for natural interaction with humans. Despite the prominence of vision-language models, they generally assume textual rather than the more natural speech inputs. In this paper, we investigate whether a well-established text-conditioned model can be transferred to speech in a data-efficient manner. Using ALBEF as a case study, we conduct diagnostic analyses showing that a lightweight MLP-based projector effectively adapts it to speech, while preserving semantic discrimination and robustness. Motivated by these findings, we introduce Speech2Grasp, a framework for data-efficient transfer of text-conditioned grasp detection to speech. Real-world humanoid robot experiments show that Speech2Grasp outperforms cascaded ASR-based pipeline, while reducing inference latency. Our findings suggest a practical paradigm for extending established text-conditioned systems to speech.

Multimodal fake news detectors often generalize poorly across domains because they learn to trust unreliable evidence: domain-specific shortcuts amplified by imbalanced data and semantically inconsistent text-image pairs that make cross-modal evidence unreliable. We propose Expert-Guided Mutual Distillation (EGMD), which learns what evidence to trust across the prediction pipeline. At the input level, input-level calibration encodes pair-level coherence as a shared gain before fusion. At the representation level, an expert-guided teacher aligns domain statistics and encourages domain-specific patterns to concentrate in specialized experts. At the decision level, prototype-anchored domain-specific students use mutual learning and dual-channel distillation to inherit the teacher's feature geometry and calibrated predictions while discouraging local domain priors. We further construct Weibo_Balanced, a domain-balanced benchmark that isolates the effect of imbalance on generalization. Across four datasets in two languages, EGMD achieves state-of-the-art accuracy while reducing domain bias by up to 57.3%.

Multimodal continual learning (MMCL) aims to learn emerging knowledge from multimodal data while preserving knowledge. To mitigate forgetting, current MMCL methods usually focus on cross-modal representation alignment or semantic similarity, but they overlook whether the relative contributions of individual modalities and their interactions remain stable across incremental tasks. We term this decision-level shift Modality Contribution Drift (MCD) and quantify it with the MCD score, which combines contribution-strength and relative-reliance changes under controlled interventions on modality subsets. Theoretical and empirical analyses further explain why current MMCL methods cannot reliably mitigate this drift. To this end, we propose Continual Modality Contribution Drift Regularization (CMCDR), which preserves the modality contribution structure of previously learned tasks. Since MMCL settings differ in whether old exemplars are available, CMCDR includes both replay-based and replay-free versions. The replay-based version uses modality-subset interventions as diagnostic probes on stored old samples, compares their contribution profiles between the current model and a frozen previous model, and constrains changes in old-sample modality-specific and interaction contributions. The replay-free version uses current-task samples as probes and distills the frozen model's old-task contribution responses, thereby regularizing the observed contribution profile without exemplars. Experiments on multimodal class-incremental learning and continual visual question answering validate the generality and effectiveness of CMCDR.

Multimodal Large Language Models have sparked significant interest due to their potential for social intelligence; however, their ability to perform sequential motivation reasoning remains insufficiently studied. Existing evaluations predominantly examine static text or isolated visual snapshots, which do not reflect the cumulative nature of real-world behavioral drivers. To address this gap, we introduce MultivationBench, a benchmark designed to rigorously evaluate multimodal motivation reasoning within story-driven visual narratives. The benchmark builds upon established psychological frameworks - Maslow's hierarchy and Reiss's basic desires - and requires models to integrate accumulated multimodal context to infer evolving motivations. Results indicate that MultivationBench presents a significant challenge: all tested models struggle to maintain consistent motivation reasoning across sequential contexts, revealing a critical disconnect between static recognition capabilities and the dynamic reasoning essential for human-like social understanding.

Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence for human inspection. Existing discriminative FAS models remain largely label-centric, while recent MLLM-based methods offer structured outputs but still rely mainly on supervised fine-tuning, often producing template-like rationales and weak optimization for difficult attacks. We propose FAS-R1, a two-stage reasoning-oriented MLLM framework for unified FAS prediction, covering authenticity classification, attack-type recognition and spoof-region localization. FAS-R1 first uses FAS-R1-23K, a high-quality long-CoT dataset, for cold-start supervised fine-tuning, and then performs FAS-specific GRPO post-training. Degradation-Simulated Augmentation (DSA) encourages stable spoof-cue reasoning across visual-quality shifts, while Difficulty-Aware GRPO (DA-GRPO) mitigates easy-sample dominance that may leave difficult task--attack groups under-optimized, especially for subtle or ambiguous attacks such as makeup and mask attacks. The main 3B FAS-R1 model achieves 98.75% authenticity accuracy, 93.33% attack-type accuracy, and 96.30/94.73% AP@40/AP@50 in-domain. It also outperforms the compared systems in cross-domain authenticity generalization and answer-and-rationale quality. Experiments with different base models further show favorable scaling behavior. The code will be released soon.

Unified multimodal models (UMMs) aim to integrate understanding and generation within a single architecture, yet it remains unclear whether these capabilities share a unified and transferable semantic space. This question is fundamentally challenging, as the two branches operate over heterogeneous representations (text tokens vs.\ visual latents) and distinct training objectives, making direct comparison difficult. To address this, we introduce \emph{cross-branch semantic steering}, an intervention-based framework that extracts semantic directions from one branch and applies them to the other. We show that steering vectors learned from the understanding branch can transfer to generation, enabling controllable image synthesis and improved semantic faithfulness. In contrast, the reverse direction consistently shows limited effectiveness. Our analysis suggests that this asymmetry may be related to a practical representational mismatch: understanding-derived vectors capture transferable, object-centric semantics, while generation-derived vectors primarily encode low-level appearance features. Our results reveal that architectural unification does not guarantee semantic alignment, and establish cross-branch steering as a practical tool for probing multimodal representations.

Graph foundation models (GFMs) have emerged as a promising paradigm for transferring knowledge across graph domains and tasks. Real-world graphs associate nodes with text, images, and other modalities, making multimodal graphs essential for representing complex entities and relations. Moreover, collecting labels and adapting models for every new graph domain is costly and often infeasible, motivating zero-shot transfer. Unfortunately, zero-shot transfer on multimodal graphs remains underexplored. Existing GNN-based graph foundation models typically require downstream adaptation, whereas LLM-based graph methods mainly address unimodal graphs or tasks within a single domain. This setting presents two key challenges. First, models must generalize knowledge from individual modalities while capturing transferable cross-modal relations. Second, without target-domain fine-tuning, node representations remain entangled with domain-specific structures and modality-specific characteristics, obscuring shared concepts in unseen domains. To address these challenges, we propose CHARM, a multimodal graph foundation model with hierarchical context modeling for zero-shot transfer. CHARM replaces isolated raw nodes with hierarchical graph contexts that capture multimodal semantics and cross-modal relations. These contexts map domain-specific node patterns to shared high-level concepts, reducing reliance on target-domain supervision or adaptation. A modality-aware graph context encoder integrates multimodal information with graph structure and converts the resulting representations into graph tokens for a large language model . Experiments show consistent improvements on zero-shot multimodal graph tasks.

Recent generative models can produce images with few obvious visual artifacts, weakening detectors and explanations that rely only on surface appearance. We present LaP-Forensics, a multimodal framework that augments RGB semantics with reconstruction-based forensic evidence. A frozen Stable Diffusion DDIM inversion-reconstruction model provides a fixed reconstruction reference, and its residual map measures local compatibility with that reference. Independent projectors encode the RGB image and residual map before a structured Where-What-Why model predicts a textual analysis and an artifact mask.Supervised fine-tuning is followed by Group Relative Policy Optimization (GRPO), whose reward combines mask overlap with output-structure and evidence-reference terms. These text-side terms encourage the model to refer to the consistency map but do not constitute a verifier of free-form textual truth. A separate image-level head fuses RGB and DDIM-residual class features. Experiments show cross-generator detection on UniversalFakeDetect and competitive artifact localization on the official SynthScars benchmark. Controlled cue-construction, inversion-horizon, component, reward-term, and counterfactual analyses support the utility of the residual stream under the evaluated settings, while free-form textual faithfulness and reliability under post-processing remain open limitations.

Ambivalence and hesitancy (A/H) are conflicting affective states that precede the delay or abandonment of health behaviour change. Recognition of A/H at the video level is difficult, since the signal arises from disagreement across and within facial, vocal, linguistic, and bodily modalities, and manifests differently across individuals. The proposed PRISM-AH (Predictive Reasoning over Interacting Streams for Multimodal Ambivalence/Hesitancy Recognition), is a framework that treats A/H as a multimodal conflict that unfolds over time. Frozen vision, audio, and text encoders are aligned into short time windows and passed to a lightweight streaming model that scores cross-modal dissonance, predicts each next window to expose a hesitation surprise signal, discovers behaviour prototypes, and is conditioned on participant metadata. Dense window-level annotations supervise the model as an auxiliary objective, and the decision threshold is calibrated for macro F1. A knowledge-guided large language model then reasons over structured evidence using the expert cue taxonomy of the dataset, and its verdict is fused late only when validation performance improves. On the labelled public test partition of 525 videos, PRISM-AH attains a macro F1 of 0.6133, compared to the reported zero-shot baseline of 0.2827. The reasoning gain is validated to transfer from validation to the larger test partition.

Wikipedia and Wikidata are widely used for information access, LLM pre-training, and retrieval-augmented generation. Their knowledge is deeply connected but scattered across text, tables, and knowledge graphs. This raises a practical question: when these modalities disagree, how can we detect and explain the conflict? We study this problem as modality-level inconsistency detection. We first introduce a taxonomy of cross-modal knowledge inconsistencies, covering information granularity differences, direct conflicts, temporal changes, and KG incompleteness. We then present Kontrast, an automatic framework that uses Text-to-SPARQL and LLM reasoning to compare table-based answers with KG evidence and categorize the resulting inconsistencies. Experiments on various Table-QA datasets show that cross-modal inconsistencies are common and informative. They reveal not only true knowledge conflicts, but also missing KG structure and temporal mismatches while being limited by Text-to-SPARQL errors and noise. Our analysis shows that text, tables, and KGs can complement and correct one another through systematic comparison. Kontrast provides a practical tool for large-scale knowledge auditing and establishes a benchmark for future work on cross-modal knowledge consistency. Code and data are available at https://github.com/ECLADATTA/KONTRAST.

Recent multimodal large language models (MLLMs), such as Qwen2.5-VL and InternVL3, generate large numbers of vision tokens for high-resolution inputs, leading to substantial computational cost. Existing vision token pruning methods either depend on cross-modal attention and cannot prune before the prefill stage, or rely on diversity estimation with high computational overhead. We observe that attention scores from both vision and text tokens peak at modality separator tokens, suggesting that these separators bridge the two modalities. Based on this observation, we propose SepPrune, an efficient, training-free, plug-and-play pruning method that uses the separator token as a unified query to rank and select informative vision tokens. SepPrune reuses the LLM's built-in projection parameters and requires no architectural changes. Experiments on Qwen2.5-VL-7B show that SepPrune achieves state-of-the-art performance, retaining 96.3% of the original accuracy while removing 80.2% of vision tokens.

Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory and inference costs. Existing compression methods mainly focus on selecting important tokens under fixed budgets, leaving the preceding budget-allocation problem underexplored. We show that direct query-to-audio/video similarity is unreliable for inter-modal budget allocation, and that uniform intra-modal budgets can miss key evidence while retaining redundant content. To address these limitations, we propose OmniDelta, a training-free, skill-driven framework that couples intent-aware inter-modal allocation with content-aware intra-modal allocation. OmniDelta first constructs audio and video skill pools to shift the fixed retained-token budget according to query demand, then reallocates modality budgets over audio segments and video frames using local complexity and temporal redundancy. The resulting local budgets can be combined with existing pruning strategies, preserving the total retained-token ratio while changing where the budget is spent. Experiments on four audio-video benchmarks with two Qwen2.5-Omni models show that OmniDelta establishes a new accuracy-efficiency Pareto frontier across pruning ratios. At 25% token retention on Qwen2.5-Omni-7B, OmniDelta reduces GPU memory by 22.0% and achieves a 1.64x end-to-end speedup over full-token inference.

Perception tasks for autonomous vehicles need to work satisfactorily in adverse weather conditions. Due to lack of real-world weather datasets, weather simulations are a promising alternative. To ensure simulations closely mirror real-world weather data, it's crucial that they represent the same weather characteristics, including severity and particle positioning, across different sensors. To achieve this, we propose the Reference Dataset Alignment Method (ReDAM) for weather intensity alignment in fog and Unified-weather-edit (inspired by Weather-edit[1]) for particle positioning alignment in rain and snow. We validate both alignment methods using statistical and geometrical tests, respectively. We find that 3D detection models for non-aligned versions tend to be overly optimistic as compared to aligned versions. We also show the aligned-multi-sensor simulation's effectiveness for achieving robustness for 3D object detection task by finetuning existing sensor fusion models on it.

Medical-imaging AI benchmarks combine datasets, DICOM rendering, prompts, provider APIs, automated labels, statistical code, manuscripts, and repository releases. Agreement across these artifacts is usually assumed rather than tested. We performed a retrospective forensic reproducibility audit of a preserved chest-radiograph vision-language model (VLM) pilot; no model was called again and no image or report was newly annotated. We traced prompt bindings, DICOM metadata, output completeness, label extraction, matched analyses, and release propagation. Of 300 planned model-prompt calls, 297 yielded nonempty reports. Sixty Claude calls labeled A/B were executed with the same C prompt. The 30 studies represented 28 patients. Four MONOCHROME1 images were rendered without required polarity inversion, dataset split membership was not retained, and the unvalidated extractor truncated five reports to 4000 characters. Reconstructing one common cohort of 369 complete case-finding blocks changed Cochran's Q from 154.73 to 182.29. Of 45 McNemar comparisons, 27 had unadjusted p < 0.05 and 20 remained below 0.05 after Holm adjustment. These values describe only the archived automated-label matrix; they do not recover the intended prompt comparison or establish clinical performance. We withdraw the original performance, ranking, prompt-effect, and clinical claims and specify machine-verifiable controls for cohort, DICOM rendering, prompt and model identity, call status, annotation provenance, keyed analysis, and derived artifacts.

Unifying visual understanding and generation in one model holds immense promise, but remains challenging and expensive due to heavy compute and data demands and conflicts between the visual features needed for these two capabilities. To address these challenges, we present Argus-Unified, a compact, effective and unified multimodal model built with low demand on computation and data. Instead of aligning modalities from scratch, Argus-Unified effectively leverages pretrained vision-language models (VLMs) that provide strong multimodal priors. Specifically, we introduce hybrid visual tokens that preserve continuous tokens for understanding while learning discrete tokens for generation from a frozen unified vision encoder. Our training pipeline includes two stages: the first stage learns a quantizer and image decoder on top of the frozen vision encoder, the second stage trains the LLM initialized from a pretrained VLM for the unified multimodal modeling. Using by far the least amount of data (15.6M) and the lowest cost (~$2,000), we demonstrate that unified multimodal models can be trained economically while achieving strong performance in both understanding and generation. Notably, our model attains state-of-the-art multimodal understanding on GQA, POPE, and VQAv2, and competitive generation quality compared to models with dedicated vision encoders (e.g., Janus, Janus-Pro), all at ~10x lower cost and with ~5x less data. We envision Argus-Unified as a useful baseline that lowers the development barrier for unified models.

The rapid advancement of video generation models has led to the increasing misuse of image-to-video (I2V) models. Although substantial progress has been made in detecting AI-generated videos, proactive defenses against I2V models remain underexplored. In particular, current proactive defenses against I2V models predominantly rely on gradient-based adversarial attacks, which require defenders to possess GPUs with substantial memory resources (VRAM) to generate adversarial examples. To address this issue, we propose I2VShield, a privacy protection method based on generative adversarial attacks tailored to Diffusion Transformer (DiT)-based I2V models. The proposed method primarily consists of two components: (1) a text-adaptive perturbation generation framework integrating adversarial learning to mitigate computational overhead while maintaining visual imperceptibility; and (2) an untargeted Multimodal Attention Disruption (MAD) attack that exploits the inherent vulnerabilities of DiT-based I2V models, maximizing the deviation of the internal attention features from their clean states. Extensive experiments demonstrate that our approach achieves highly competitive protection performance across various datasets and mainstream DiT-based I2V models, particularly in disrupting spatiotemporal coherence, while substantially reducing computational costs.

Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external corpora, and full cross-modal fusion. Existing systems pay all three costs uniformly per query, even though only a small fraction of visual content and retrieved knowledge is actually relevant to any given question. We introduce SKIP (Salient Knowledge-Injected Pathways), a unified inference architecture that routes computation along sparse pathways jointly conditioned on the question, the image, and a difficulty estimate. SKIP combines question-guided visual token pruning, region-conditional sparse retrieval, bipartite sparse cross-attention, and speculative knowledge verification with an adaptive budget controller that allocates compute proportional to predicted question difficulty. We derive an information-bottleneck bound showing that the optimal visual sparsity rate scales as $O(1/\sqrt{N})$ under realistic question-image mutual-information assumptions, with retained accuracy guarantees. Across five KI-MMQA benchmarks (OK-VQA, A-OKVQA, InfoSeek, Encyclopedic-VQA, and ViQuAE), SKIP matches or exceeds the accuracy of strong dense baselines while using $3.4$--$6.8\times$ fewer FLOPs and $2.7\times$ less end-to-end latency. Code available at: https://pmlrbd.github.io/skip/

Histopathological examination primarily relies on hematoxylin and eosin (H&E) and immunohistochemistry (IHC) staining. Although IHC provides critical molecular information, it is costly and requires specialized expertise. Stain transfer provides an efficient alternative by computationally generating IHC from H&E images, but remains challenged by unified and interpretable modeling for heterogeneous biomarkers under pixel-unaligned supervision. We propose DMCoStain, a novel Data-Model Co-optimization framework for Stain transfer. It iteratively co-refines training data and model capability, improving staining accuracy and interpretability in both pathological and structural consistency. To refine training data in a clinically meaningful manner, it incorporates the Multimodal Expert-Guided Finer Selection (MEGFS) strategy, built upon a pioneering IHC-positive-expression (IPE) vision-language model (VLM) that emulates pathologist reasoning. To support MEGFS, we construct ImmunoInstruction, the first large-scale IPE instruction-following dataset with 150K VQA samples. Extensive experiments on multiple tissues and biomarkers demonstrate that DMCoStain achieves state-of-the-art (SOTA) accuracy. This paradigm offers strong practical value, and MEGFS also functions as a specialized evaluation tool for future model development. Dataset, code, and more details are in https://github.com/SikangSHU/DMCoStain.

Multimodal large language models (MLLMs) have enabled long-form video understanding at a scale that was not previously possible. However, the density of relevant content decreases sharply as video sequence length increases, and exposing the model to more irrelevant content measurably reduces its accuracy. In this paper, we address the problem of maximizing query-relevant information in a frame subset selected at inference time, without training. FORGE (Frame Orthogonality in Relevance Geometry) is a model-agnostic method that induces a query-conditioned geometry on a pretrained multimodal embedding space, unifying relevance and diversity into a single objective. In this space, frames that cover independent query-relevant directions are far apart, and selecting the subset of maximum information captures diverse query-relevant content within the budget. Experiments on Video-MME and LongVideoBench at budgets of 16, 32, and 64 frames show that FORGE improves the unified keyframe selection score by 11.0-15.3 points over the strongest training-free baseline and up to doubles keyframe recall (0.415 vs. 0.204 at K=64 on Video-MME). The gains extend to question answering, where accuracy improves in every evaluated setting across eight open-source MLLMs spanning 4B to 32B parameters, by up to 8.7 points over uniform sampling and 5.2 points over the strongest baseline. Our findings suggest that aligning the embedding space with the query's high-dimensional structure is a promising direction for inference-time video understanding.

Referring multi-object tracking (RMOT) extends tracking from category-driven perception to language-guided understanding by grounding object trajectories in natural-language expressions. Despite recent progress, existing RMOT studies are largely conducted under in-domain settings, leaving the robustness of language-conditioned tracking under inevitable visual domain shifts unexplored. In this paper, we study Cross-Domain Referring Multi-Object Tracking (CD-RMOT), a new and challenging problem that evaluates whether an RMOT model trained on a labeled source domain can reliably follow natural-language expressions in an unlabeled target domain with different visual conditions. To support systematic study, we construct CD-RMOT-Bench, a unified benchmark that combines real clear-domain referring tracking data, aligned digital-twin variants, and real adverse-domain videos. CD-RMOT-Bench enables both controlled weather/viewpoint shift analysis and realistic synthetic-real transfer evaluation under a shared RMOT protocol. Further, we provide a Query-Centric Adaptation (QCA) framework, designed to stabilize the query space that bridges visual trajectories and referring expressions. Extensive experiments reveal that domain shifts severely degrade RMOT performance, where the failure is not merely caused by object detection errors but more critically by unstable expression-conditioned temporal association and target selection. QCA establishes a strong baseline, while CD-RMOT-Bench opens a new direction for robust language-guided tracking across visual domains.

Digital phenotyping (DP) using smartphones and wearable devices has shown considerable potential for mental health monitoring. However, progress remains difficult to evaluate due to heterogeneous datasets, inconsistent preprocessing pipelines. In this work, we present a reproducible benchmark built upon the Neurai-VN dataset, a high-resolution, multimodal dataset comprising passive sensing and active assessment from wearable and smartphone devices, collected from 100 Vietnamese adults over two weeks. We define four binary classification tasks evaluated using standardized subject-wise cross-validation. Representative linear, tree-based, and neural baseline models are evaluated systematically across predefined feature-group configurations. Mean subject-level F1 scores across five cross-validation folds reached 0.71 for Healthy Control vs. Depression and Healthy Control vs. Clinical, while Healthy Control vs. Anxiety and Depression vs. Anxiety achieved 0.69 and 0.56, respectively. These baseline results provide reproducible baselines for future research on multimodal DP for mental health classification tasks.

Despite rapid progress in Multi-modal Large Language Models (MLLMs), understanding long-form videos is still bottlenecked by limited context windows. While recent keyframe sampling methods attempt to mitigate this by distilling video inputs into a compact set of query-relevant frames, navigating the vast spatio-temporal search space remains challenging, as spatial detail and temporal coverage often conflict. To address this, we introduce LENS, a training-free keyframe sampling framework that dynamically decides when to zoom in for fine-grained details and when to zoom out for broader context based on the text query. Concretely, LENS adaptively allocates a limited frame budget between spatial zoom-ins, which highlight query-relevant regions within individual frames, and temporal zoom-outs, which expand the temporal scope through multi-frame aggregation, enabling the model to reason across multiple granularities while capturing both high-fidelity details and long-range context. Across diverse long-form video benchmarks, LENS consistently outperforms prior state-of-the-art keyframe sampling methods and delivers substantial gains over uniform sampling, improving Video-MME accuracy from 53.3% to 60.7% with Qwen2.5-VL.Code is available at https://github.com/zhangce01/LENS.

Multi-modal large language models (MLLMs) integrate heterogeneous modalities through modality alignment and fusion, enabling stronger understanding and reasoning. However, this architectural shift reshapes the safety landscape of machine learning. Increased model complexity and cross-modal interactions give rise to novel threats, including compromised modality integration, modality misalignment, and fused safety risks, reflecting shifts in threat modeling beyond uni-modal assumptions. These shifts, in turn, impose new constraints on safety solutions not captured by existing frameworks rooted in uni-modal learning. Motivated by these challenges, this survey provides a systematic analysis of the evolving safety landscape of MLLMs. We first propose a multimodal grounded taxonomy of safety threats and analyze shifts in threat models, covering adversarial attacks, data poisoning, jailbreaks, and hallucinations. We then summarize updated safety assumptions and organize recent advances in MLLM safety strategies accordingly. Finally, we discuss open challenges and future directions to inform the development of more principled and scalable safety mechanisms for multimodal systems.

Standard vision-language models (VLMs) suffer from Moravec's paradox: they excel at complex offline visual reasoning but struggle with simple streaming perception tasks and process them inefficiently. We present Mage-VL, an efficient codec-native streaming foundation model for real-time multimodal understanding and interaction. At its core, our custom tokenizer, Mage-ViT, replaces uniform frame sampling by selectively encoding dynamic, entropy-rich regions using motion vectors and residual energy across sparse anchor (I) and predicted (P) frames. Operating at a 16 x 16 patch level, this reduces visual token consumption by over 75% while preserving spatiotemporal context. Trained from scratch on approximately 560M unlabeled images and 100M unlabeled video frames, Mage-ViT matches or outperforms flagship encoders trained on billions of image-text pairs. We establish AI4AI data pipelines encompassing prompt-code joint optimization for multimodal captioning and AI-driven performance diagnosis to guide training recipes. Furthermore, through a bio-inspired dual-system architecture - a lightweight System 1 event gate and a causal System 2 decoder - Mage-VL enables proactive streaming perception. Extensive evaluations show that Mage-VL-4B matches Qwen3-VL-4B on static tasks while achieving strong gains in video understanding and 2D/3D spatial reasoning, with up to a 3.5x wall-clock inference speedup, and comprehensively surpasses the 15B Phi-4-reasoning-vision baseline. Beyond model artifacts, we deliver seven key empirical findings covering pre-training data efficiency, variable-resolution scaling, codec system acceleration, VideoQA SFT redundancy, motion-spatial synergy, AI4AI data pipelines, and Zero-Vision SFT for multimodal RL.

Multimodal large language models (MLLMs) hold immense potential to revolutionize clinical practice, yet deploying them in the medical domain is fundamentally a vision-centric challenge: models must absorb knowledge from heterogeneous 2D and 3D medical images, and evaluation protocols must align with radiologists' clinical practice and provide an accurate, fine-grained and factualness-driven assessment. In this paper, we introduce ClinFusion, a vision-centric MLLM designed for holistic medical understanding that systematically addresses these limitations. We propose a compositional and cascaded vision encoder architecture featuring a Cascade Spatial-Aware Locality Fusion operator that unifies diverse 2D and native 3D medical image understanding within a fused encoder. We further introduce a vision-grounded evaluation framework, including MedIF-Bench for instruction-following assessment and a region-of-interest-grounded method for clinically aligned and factualness-driven report generation evaluation. We show that ClinFusion sets a new state-of-the-art across a comprehensive suite of 2D and 3D multimodal medical benchmarks---spanning visual question answering, report generation, and instruction following---as well as textual medical tasks, outperforming leading open-source medical MLLMs (\textit{e.g.}, Hulu-Med, Lingshu) on 20 out of 24 benchmarks and demonstrating multimodal capabilities better than powerful proprietary models such as GPT-5.2 and Gemini-3-Flash on 13 out of 16 benchmarks, and can be further augmented with agentic tool use for retrieval-augmented and tool-assisted clinical workflows. A blinded evaluation by board-certified radiologists confirms that ClinFusion produces the highest-ranked reports, and validates our RoI-grounded metric as achieving the strongest correlation with expert judgment among all automatic evaluation metrics examined.

Multimodal Large Language Models have made great progress in grounding tasks, yet existing methods still struggle to unify precise localization and complex reasoning. For one thing, text-based methods rely on coordinates or index prediction, severely limiting the perceptual capabilities of the model for dense visual objects. Meanwhile, latent token-based methods employ special tokens without inherent spatial references and use a decoding mechanism that lacks thinking steps, weakening high-level reasoning capabilities. Consequently, developing a unified framework that excels in both perception and reasoning remains challenging. To address this, we propose Mixture-of-Thought-Tokens (Motto), a new free-form multimodal grounding method that bridges the perception-reasoning gap, enabling MLLMs to empower diverse, arbitrary grounding queries. Specifically, we introduce Spatially-Grounded Thought Tokenization to explicitly align special tokens with spatial locations for clear spatial correspondence and visual interpretability. We further design a Context-Adaptive Chain-of-Tokens that dynamically switch grounding modes within an interleaved reasoning chain, achieving robust grounding across tasks of varying complexity. In addition, we construct PR-Bench, a new referring expression comprehension benchmark to evaluate the perception-reasoning gap. Extensive experiments demonstrate that Motto achieves state-of-the-art performance across diverse free-form grounding tasks.

Real-time long-form digital-human generation relies on causal models to extend audio-visual content while preserving subject appearance and audio-video synchronization across successive segments. A bounded cache retains local motion and phonetic context but discards older evidence, whereas attending to the complete generated history is computationally expensive and can propagate accumulated errors. We present \method, an anchor-guided persistent-memory framework for few-step joint audio-video generation. The framework preserves an immutable visual anchor, compresses completed video and audio blocks into fixed-capacity dynamic states, and retrieves those states through modality-specific residual attention without extending the active cache. A reference-aware modulation method additionally conditions video features on dynamic and anchor appearance statistics. Anchor-preserving causal-context distillation varies rollout horizon, prefix provenance, and cache-history reliability while keeping the immutable visual anchor unperturbed. By separating persistent memory from stage-local denoising dependencies, \method further admits stage-parallel execution across blocks, accelerating autoregressive inference without pipeline-specific retraining. We evaluate long-form video continuations with appearance, temporal, synchronization, facial, and speech diagnostics. Results show that \method preserves stable appearance across prompt-conditioned segments and strong audio-visual synchronization under autoregressive generation. Our project page is https://taoliveaigc.github.io/TaoMate.

Automatic prompt optimization (APO) has been widely adopted to adapt vision-language models (VLMs) to downstream tasks without weight updates, yielding promising results. However, on multimodal tasks, the effectiveness of APO is fundamentally bottlenecked by a blind feedback channel: the optimizer reads the question, the prediction, and the gold answer, but never the input image on which the model failed, and therefore cannot diagnose visually grounded errors. As a remedy, we introduce Cross-Modal Visual Feedback (CMVF). CMVF incorporates (1) a failure-conditioned visual diagnosis stage, in which a stronger optimizer VLM inspects each failed image without access to predictions or labels, and (2) an error-aware aggregation stage that compresses these observations into reusable, task-level visual blind-spot patterns that drive the prompt rewrite. Crucially, the image is consumed only during optimization; the deployed artifact is an ordinary text prompt that runs at the same inference cost as any text-only baseline. Extensive results across 12 VQA datasets and 4 target VLMs demonstrate that CMVF consistently ranks first, improving over the strongest baseline on every target by 2.4 points on average, with gains of up to 6.5 points on individual benchmarks. Moreover, the optimizer self-organizes into expert-style visual checklists that transfer across models without re-optimization.

Multi-modality data from different sensors provides rich complementary information for 3D perception, becoming an essential component in reliable autonomous driving systems. Current research typically designs intricate and complex fusion strategies to integrate information from multimodal data on a unified bird's-eye-view (BEV) feature map for the joint learning of multiple perception tasks. However, such a single feature map hardly carries sufficient information to simultaneously meet the requirements of various perception tasks, leading to a very limited perception performance. To mitigate this limitation, this paper proposes MATS, a novel multi-modality multi-task learning approach with modality-adaptive BEV fusion and task-specific Mixture-of-Experts (MoE) for 3D perception. Specifically, a simple modality-adaptive BEV fusion module is designed to adaptively recalibrate the BEV features by modeling the global cross-modality dependencies, generating diverse BEV feature maps for various perception tasks. For joint multi-task learning, this paper proposes a task-specific MoE module to decouple the tasks and enable the network to automatically choose the appropriate BEV feature candidates for each specific task. To validate the effectiveness of the proposed approach, we conduct extensive experiments on the large-scale benchmark nuScenes. With the camera- and LiDAR-modality input data, the proposed approach outperforms the state-of-the-art (SOTA) by a significant margin. Furthermore, the experimental results on the single tasks show that the proposed approach significantly outperforms the baselines. The code and trained models will be available upon publication.

Conversational stance detection has shifted from static text analysis to dynamic multimodal modeling. However, existing benchmarks exhibit three key limitations: failure to capture the dynamic evolution of beliefs, particularly during stance reversals; difficulty in disentangling affective states from logical reasoning; and neglect of the critical role of multimodal cues in resolving pragmatic ambiguities such as sarcasm. To address these limitations, we propose StanceFlip, a benchmark designed for multimodal conversational stance flipping forecasting over multi-turn dialogues across five modalities and multi-scenarios, which includes two novel subtasks: 1) Multimodal Stance Sextuple Extraction, extracting holder, target, emotion, sentiment, stance, and rationale as static state snapshots of dialogue to capture fine-grained cognitive structures. 2) Dynamic Stance Flip Attribution, tracking stance reversals across the conversation and identifying their underlying triggers. Alongside the dataset, we propose a dedicated framework, named ConStaFF, for Multimodal Conversational Stance Flipping Forecasting (MCSFF). Built upon a large language model, ConStaFF performs end-to-end stance reasoning, with a Thought-of-Stance (ToS) reasoning framework and a self-reflective verification mechanism integrated for structured stance modeling and faithful flip attribution. Specifically, ToS decomposes the reasoning process into specialized cognitive personas to formulate target propositions, resolve cross-modal conflicts, and infer historical stance trajectories. Extensive experiments show that our approach achieves state-of-the-art performance on both sextuple extraction and flip-trigger attribution, outperforming strong multimodal large language model baselines by substantial margins.

The empirical success of attention mechanism in Multimodal Large Language Models (MLLMs) often obscures its inherent, subtle flaws. Specifically, MLLMs consistently exhibit disproportionate attention toward certain semantically uninformative visual tokens, a phenomenon termed "register" or "Visual Attention Sinks." While existing inference intervention methods attempt to identify these sink tokens and redistribute their attention weights, such approaches typically treat these tokens in isolation and suffer from computational inefficiency. Instead, we reframe this phenomenon as a generalized textual bias exerted over visual features that extends beyond isolated sink tokens. From this perspective, a pervasive structural bias leads to the dilution of the semantic visual signal, precipitating multimodal hallucinations as the model prioritizes linguistic priors over valid visual evidence. To address this limitation, we introduce Saliency-guided Purification and Adaptive Redistribution (SPAR), a training-free, plug-and-play intervention. SPAR mitigates this generalized textual bias by purifying structural noise and subsequently redistributing the reclaimed attention budget to the most informative visual regions. Comprehensive evaluations across a diverse spectrum of hallucination benchmarks demonstrate that SPAR effectively restores authentic visual grounding with negligible computational overhead.