Multimodal Large Language Models

Also known as MLLM

Follow this topic Ask about this topic

Momentum

67 papers in the last four weeks, up 91% on the four weeks before. 0.7% of all new papers.

Jul 13Week of Sep 28

Latest papers 676

Jul 27, 2026cs.AI

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models

Human visual reasoning typically follows a coarse-to-fine attention process, starting from global scene understanding and gradually focusing on question-relevant regions. However, multimodal large language models may deviate from this pattern due to attention drift and the underutilization of visual evidence, which can lead to hallucinations. To mitigate these issues, this study proposes a Dual-Indicator Guided Contrastive Alignment (DICA), which tracks two information-theoretic indicators during inference: Visual Attention Entropy (VAE), which reflects the concentration of visual attention, and Output Image Correlation (OIC), which measures the dependence of generated outputs on the visual input. An abnormal increase in VAE or a decrease in OIC corresponds to different failure modes, which trigger targeted contrastive alignment to restore visual grounding. Experimental results across multiple benchmarks demonstrate that DICA consistently outperforms existing approaches and substantially reduces hallucinations, highlighting the effectiveness of indicator-driven intervention in improving multimodal inference reliability. The code is publicly available at https://github.com/BGWH123/DICA/.

Hao Yang, Jin Wang, Xuejie Zhang

School of Information Science and Engineering Yunnan University Kunming, China

LLM Alignment Multimodal Large Language Models Visual Grounding VLM Hallucination Mitigation

Jul 26, 2026cs.AI

Verification-Notebook Learning for Source-Aware Multimodal Misinformation Detection

Multimodal misinformation verification is challenging because misleading signals may come from different parts of a post and require different forms of evidence. LVLMs are well suited to this task, but their verification performance often depends on the inference procedure applied to each instance. Existing methods improve this procedure through stronger prompting, retrieval, or deliberation, but rarely retain the verification patterns learned from previous examples. We propose Verification-Notebook Learning (VNL), a non-parametric framework that learns an external verification procedure for a frozen LVLM before inference. VNL builds a compact notebook of decision principles, evidence cues, and recurring pitfalls from prior verification experience. The notebook remains fixed during inference and guides the verification of new examples. Rather than updating model parameters or storing demonstrations, VNL records learned knowledge in an artifact that can be inspected directly. Experiments show that VNL consistently outperforms a range of competitive baselines. Further analyses show that the Verification Notebook improves fine-grained source attribution while remaining compact and interpretable, providing an effective way to accumulate verification knowledge without model training.

Junyuan Tan

Independent Researcher

Multimodal Large Language Models

Jul 26, 2026cs.CV

Omni-Prune: Query-Aware Unified Token Pruning for Efficient Omnimodal Large Language Models

Omnimodal large language models (OmniLLMs) are rapidly extending multimodal reasoning to cover synchronized audio and video. However, the resulting audio-video token sequences are long, leading to high prefill latency and GPU memory usage at inference time. Existing token pruning methods, designed mainly for vision-only inputs, miss both the cross-modal links between audio and video and the user query that decides which content matters. To bridge this gap, we present Omni-Prune, a training-free, query-aware audio-visual token pruning framework that jointly removes redundancy from both modalities while keeping task-relevant cross-modal evidence. Specifically, Omni-Prune first splits the token sequence into adaptive time windows placed at audio saliency peaks, then scores audio and video tokens on a single scale that combines encoder attention with text-query relevance, and pairs related audio-video tokens so that they are kept together. Within each window, a final K-medoids step then selects a few representative tokens, adding diverse cues that score-based selection alone would miss. Extensive experiments demonstrate that Omni-Prune outperforms established baseline methods, delivering up to 3.25x prefill speedup and 1.3x memory reduction while retaining over 99% of full-model performance.

Yiming Zhong, Chang Nie, Caifeng Shan

1Nanjing University

Efficient Multimodal Inference Multimodal Large Language Models Token Pruning Multimodal Token Compression

Jul 25, 2026cs.CV

OmniScope: Modality-Decoupled Token Compression for Omnimodal Large Language Models

Existing token compression methods for omnimodal large language models typically rely on one modality to determine what to retain in the other. We show that this assumption often breaks down: for the same query, audio and video relevance often peaks at different moments. This cross-modal salience mismatch makes unidirectional guidance prone to discarding answer-critical cues under aggressive compression. We propose OmniScope, a training-free token compression framework that uses the query as a shared semantic anchor while estimating relevance separately for audio and video. OmniScope allocates modality-specific token budgets, prunes visual tokens with an anchor-delta strategy that preserves both global context and temporal changes, and merges audio tokens within each second to reduce redundancy while maintaining temporal continuity. Across four audio-video benchmarks and two Qwen2.5-Omni model scales, OmniScope achieves the best average accuracy across all compression settings. At 25% overall token retention, it delivers up to 3.53x prefill speedup and more than 15% GPU memory reduction, with only a 0.35-point drop in average accuracy. These results suggest a simple design principle for OmniLLM inference: share the query across modalities, but not the salience estimates. The code is available at https://github.com/MAC-AutoML/OmniScope.

Jinsen Su, Yongdong Luo, Yuexiao Ma +3

Media Analytics and Computing Lab, Xiamen University, Xiamen, China · Institute of Artificial Intelligence, Xiamen University, Xiamen, China · School of Informatics, Xiamen University, Xiamen, China +1

Efficient Multimodal Inference Audio Token Compression Multimodal Large Language Models Multimodal Token Compression Visual Token Pruning

Jul 24, 2026cs.CV

Filling Before Advancing: Capability-Gap-Driven Post-Training for Scenario-Specialized Remote Sensing MLLMs

Remote sensing multimodal large language models (RS-MLLMs) have improved general aerial-image understanding. However, Earth observation applications require fine-grained scenario specialization, constrained by scarce high-quality scenario data and incomplete capability coverage. We formulate this adaptation as a capability-gap-driven post-training problem and propose filling before advancing (FBA). Rather than relying on single-stage supervised fine-tuning (SFT) over target-domain samples, FBA first fills prerequisite capability gaps before advancing toward scenario specialization. We instantiate FBA for coastal harbor understanding, a representative multi-source scenario, by constructing CPRS (Coastal-Port Remote Sensing), a three-layer supervision dataset coupled with three ordered stages: (1) RS semantic anchoring for overhead-view visual-language alignment; (2) domain-bridge convergence for shared RS priors across target and bridging scenarios under different modalities; and (3) evidence-grounded scenario tuning for downstream performance. We construct HarborEval, an eight-track diagnostic benchmark covering perception, spatial understanding, robustness, and generation. Under comparable training budgets, HarborEval increases from 57.95 with Direct-SFT to 70.29 with FBA on LLaVA-v1.5, and from 81.09 to 83.37 on Qwen3-VL. FBA also outperforms Collapsed-SFT and leads on harbor-related VRSBench/RSVQA subsets and OpenEval. Stage-wise and role-replacement analyses validate progressive gap filling and stage-specific roles. Public examples and release updates for CPRS, HarborEval, code, and trained weights are available at https://github.com/Z0ngL1ng/filling-before-advancing.

Yuheng Zong, Minghua Wang, Xin Zhao +3

The Institute of Robotics and Automatic Information System (IRAIS), the Tianjin Key Laboratory of Intelligent Robotics (tjKLIR), Nankai University, Tianjin 300071, China · The College of Artificial Intelligence, Nankai University, Tianjin 300071, China · Hyperspectral Computing Laboratory, Department of Technology of Computers and Communications, Escuela Politécnica, University of Extremadura, Cáceres, Spain +1

Remote Sensing Image Understanding Fine-Tuning VLM Adaptation Multimodal Large Language Models Remote Sensing Benchmarks

Jul 24, 2026cs.AI

Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents

Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, yet it remains unclear how well general-purpose models can solve long-horizon embodied tasks from a single high-level instruction. We introduce MissionBench, a benchmark for mission-level evaluation of MLLMs in aerial 3D environments. It comprises 120 missions across five simulated 3D environments and four task families. Agents must autonomously plan, navigate, and report outcomes using only egocentric observations and its action history, without aerial-specific fine-tuning. Across 22 open- and closed-source MLLMs, the strongest model succeeds on fewer than 35% of missions compared to 84.4% human performance, highlighting the difficulty of multi-step embodied tasks. Despite large variations between model families, we observe gains from scaling, indicating that larger general-purpose models possess stronger zero-shot embodied capabilities. Our analysis shows that mission-level competence requires coordinating multiple capabilities beyond spatial perception, including multi-step planning and adaptive reasoning. This motivates closed-loop evaluation and highlights both the promise and risk of scaling-driven improvements for embodied AI.

Suman Navaratnarajah, Taehyoung Kim, Jona Ruthardt +5

University of Technology Nuremberg · Fraunhofer IVI · THWS +1

Zero-Shot Learning Multimodal Large Language Models Long-Horizon Agent Evaluation AI Agent Benchmarks

Jul 23, 2026eess.SP

Toward Generalizable Cognitive Impairment Detection with Speech-Based Multimodal Large Language Models

Cognitive impairment (CI) is a growing public health concern. Early and accurate diagnosis is critical for enabling timely intervention and improving patient outcomes. Speech-based CI detection has emerged as a promising non-invasive approach, as speech signals encode both linguistic and acoustic markers associated with cognitive decline. Recent advances in large language models (LLMs) further strengthen the potential of speech-based assessment by enabling more expressive representation learning and improved generalization across diverse speakers, recording devices, and clinical environments. Moreover, multimodal learning by jointly modeling linguistic and acoustic features allows for a more comprehensive characterization of cognitive and behavioral changes related to CI, leading to more reliable detection. In this work, we propose a multimodal CI detection framework based on open-source LLMs that integrates speech audio and corresponding transcripts while preserving patient privacy. Acoustic embeddings are extracted directly from speech signals, while textual embeddings are generated from automatically transcribed speech. These modality-specific embeddings are then concatenated to create a combined feature vector and used for downstream classification, without requiring access to raw or sensitive patient data. The proposed approach is evaluated on the ADReSS20 and ADReSSo21 benchmark datasets. Experimental results show that the proposed multimodal framework achieves an CI classification accuracy of 92.4% and consistently outperforms single-modality baselines. Our work establishes a new state-of-the-art for CI identification, with the proposed method demonstrating superior cross-dataset generalization. This advance highlights the power of an LLM-based multimodal framework that fuses linguistic and acoustic data to enable robust, scalable, and non-invasive screening.

Yingchao Huang, Xin Wang, Yuhan Su +1

Faculty of Digital Innovation, Arts & Sciences, Saskatchewan Polytechnic, Regina SK S4S 5X1, Canada · School of Basic Medical Sciences, Hebei University, Baoding 071000, China · Department of Civil & Environmental Engineering and School of Mining & Petroleum Engineering, University of Alberta, Edmonton AB T6G 2H5, Canada

Multimodal Large Language Models Speech-Based Dementia Detection Multimodal Classification

Jul 23, 2026cs.CV

Unlearning Under Imbalance: Benchmarking Fairness in Multimodal LLM Unlearning

Machine unlearning has emerged as a tool for removing personal data from trained models to comply with recent AI regulations. To evaluate unlearning effectiveness in multimodal large language models (MLLMs), prior works fine-tune models on fictitious identities, simulating unlearning requests on subsets of these IDs, which are typically uniformly distributed. However, in realistic scenarios, people from different demographic groups may request to be unlearned at different frequencies, potentially altering the model's internal beliefs for these groups and leading to biased behaviors. To fill this gap, we propose FAIRGET, the first Visual Question Answering benchmark that evaluates unlearning under unbalanced, realistic, forget requests. These requests are designed to simulate multiple realistic scenarios, ranging from simple to challenging settings, that lead to biased unlearned models if fairness is not accounted for. Additionally, we propose FAUN, the first unlearning algorithm for MLLMs that forgets unlearning data while preserving model fairness. FAUN exploits a bias-aware activation steering mechanism to unlearn identities while accounting for the unbalanced nature of the forget data. Experiments on FAIRGET and the established FIUBench demonstrate our method's superiority both in unlearning quality and fairness.

Lorenzo Orsingher, Thomas De Min, Massimiliano Mancini +2

University of Trento, Trento, Italy · Fondazione Bruno Kessler, Trento, Italy

VLM Unlearning Algorithmic Fairness Multimodal Large Language Models MLLM Unlearning Machine Unlearning Multimodal Model Evaluation+1

Jul 23, 2026cs.CV

Out of Sight, Still in Mind: Token Compression for Omni-LLMs

The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but the cost of the three streams is highly unbalanced: visual tokens account for the vast majority of the input, and are highly redundant. In this paper, we propose ReMo, a training-free framework that compresses visual tokens by redistributing their information across modalities: a visual token is kept only if its information appears nowhere else. ReMo achieves this in two ways: (i) it aligns audio and video in a common embedding space, and removes visual tokens already explained by the audio or by other visual tokens; and (ii) it replaces object-level visual tokens with compact text proxies, short descriptions of each object and its location, conveying the same content in far fewer tokens. On Qwen2.5-Omni at two model scales, ReMo removes 54% of the input tokens with no loss in accuracy. Indeed, it slightly exceeds the full-token model, reaching 101.2% and 101.3% of its average accuracy over five audio-visual benchmarks.

Suho Yoo, Youngjoon Jang, Hyebin Cho +1

KAIST · VGG, University of Oxford

Efficient Multimodal Inference Multimodal Large Language Models Multimodal Token Compression Video Token Compression Visual Token Pruning Visual Token Compression

Jul 23, 2026cs.CV

Geo3R: Mitigating Spatial Reasoning Hallucination in Multimodal Large Language Models

Despite remarkable progress in visual understanding, Multimodal Large Language Models (MLLMs) remain prone to hallucinations when reasoning about spatial relationships, often producing judgments that contradict the true 3D structure of the scene. Though several existing works have proposed to mitigate hallucinations, our analysis indicates that they show limited effectiveness in spatial reasoning, as they fail to bridge the fundamental gap between 2D visual representations and 3D spatial reality. Based on this finding, we define hallucinations arising from insufficient spatial structure modeling as spatial reasoning hallucination, a subcategory of relation hallucination that existing mitigation methods fail to address. We further identify three typical scenarios where such hallucinations frequently occur: perspective effects, object orientation, and viewpoint changes. To this end, we propose Geo3R, a training-free, plug-and-play framework that incorporates geometric evidence and structured 3D reasoning to mitigate spatial reasoning hallucination. Experiments on three benchmarks, covering 18 tasks across all three scenarios, show that Geo3R substantially reduces spatial reasoning hallucination across diverse MLLMs without additional training, outperforming existing models and methods.

Mingyu Wang, Weilin Jin, Wenbo Li +3

Peking University Beijing, China · Joy Future Academy Beijing, China

3D Spatial Reasoning Hallucination in Language Models Multimodal Large Language Models VLM Hallucination Mitigation

Jul 23, 2026cs.AI

EmoAgent-R1: Towards Multimodal Emotion Understanding with Reinforcement Learning-based Dynamic Agent Specialization

Multimodal large language models (MLLMs) have achieved impressive performance in multimodal emotion recognition (MER) tasks and lifted MER to a new level that is complex emotion understanding with advanced video understanding abilities and natural language description. However, existing MLLM-based methods often use a fixed prompt to perceive the emotions, ignoring the dynamicity and complexity of the emotion source in the multimodal inputs. To address these issues, we propose a novel Reinforcement Learning-based Dynamic Agent Specialization framework (\textbf{EmoAgent-R1}) to optimize the emotion recognition, reasoning, and generalization abilities of an MLLM with dynamic agent specialization based on reinforcement learning. Specifically, we first adopt a cold start strategy to endow an MLLM with preliminary emotion recognition, reasoning, and agent routing ability by training with synthetic answer-conditioned chain-of-thought data and agent routing data. Then, we further train the MLLM with reinforcement learning to perceive emotions in a two-step agentic workflow with agent selection and agent specialization. To effectively train EmoAgent-R1, we propose a novel Progressive Group-Relative Policy Optimization (P-GRPO) to combine group-based relative advantages with a PMI-inspired progressive token-level modulation to transform sparse rewards into fine-grained learning signals, mitigating the coarse-grained uniform credit assignment issue in GRPO. Extensive experiments on MER benchmarks demonstrate the superiority of our EmoAgent-R1 in stronger emotion reasoning performance and improved optimization stability.

Lihuang Fang, Yuchen Zou, kebing Jin +1

Guangdong University of Technology Guangzhou, China · Southern University of Science and Technology Shenzhen, China · Xi’an Jiaotong University Xi’an, China +1

RL for Language Models Agentic RL Multimodal Large Language Models Multimodal Emotion Recognition

Jul 23, 2026cs.AI

Enhancing Explainable Cardiac Diagnosis with Guide-Grounded Multimodal LLMs

The electrocardiogram (ECG) is a cornerstone of cardiac as- sessment, yet clinical deployment of deep learning models remains con- strained by limited interpretability and the hallucination risk of large language models (LLMs). Existing CNN+Grad-CAM+multimodal LLM frameworks can generate ECG reports, but their explanations are often only weakly grounded in established diagnostic criteria, reducing trust- worthiness and reproducibility. We propose a guide-grounded multimodal framework that explicitly anchors report generation in curated clinical knowledge. A convolutional neural network (CNN) and Grad-CAM first produce class probabilities and class-specific heatmaps from 12-lead ECG images. In parallel, authoritative ECG textbooks and guideline materials are distilled offline into a structured ECG Interpretation Guide, which is injected as a fixed knowledge block for every sample. Conditioned on the ECG image, Grad-CAM overlay, CNN-derived fact pack, and the in- jected guide, a multimodal LLM generates structured diagnostic reports with guideline-consistent terminology and criteria usage. Experiments on the full PTB-XL test set demonstrate that guide grounding improves se- mantic quality and perceived consistency of generated reports while pre- serving competitive classification performance. In particular, our method increases the average BERTScore of generated impressions from 0.818 to 0.953 relative to a strong CNN+Grad-CAM+MLLM baseline, indicat- ing closer alignment with reference reports. These findings suggest that injecting a distilled interpretation guide into the multimodal prompting pipeline offers a practical pathway to reduce hallucinations and enhance the clinical plausibility of LLM-based ECG explanations, bringing ex- plainable cardiac diagnosis closer to real-world deployment.

Hai-Nam Duy Vuong, Duy-Anh Bui, Trong-Nghia Nguyen +5

Business AI Lab, College of Technology, National Economics University, Vietnam · FPT University, Hanoi, Vietnam · A2I Lab, Phenikaa School of Computing, Phenikaa University, Hanoi, Vietnam +2

Multimodal Grounding Medical Report Generation Electrocardiography Multimodal Large Language Models Electrocardiogram Classification

Jul 22, 2026cs.CV

Look Less, Think Faster: Joint Token-Compute Adaptation for Multimodal LLMs

Multimodal Large Language Models (MLLMs) have recently demonstrated strong performance across vision-language tasks. However, their high inference cost, arising from both the large number of input visual tokens and the heavy computation of the large language model (LLM), remains a key barrier to practical deployment. Recent work attempts to reduce the cost by adaptively optimizing individual dimensions, e.g., pruning redundant visual tokens or skipping LLM layers and heads. Nonetheless, prior approaches typically treat these dimensions independently and overlook a fundamental coupling: the available compute resources must be dynamically allocated across all dimensions based on the input content. To bridge the gap, we propose SmartVL, a unified adaptive inference framework that jointly controls vision token number and model compute capability in response to varying input contents and compute budgets. SmartVL introduces a vision-side token controller that dynamically selects informative visual tokens and an LLM-side compute controller that adaptively adjusts LLM computation. Importantly, these controllers are trained to coordinate with each other so that the overall inference cost satisfies a target budget. To allow this joint scheduling, we connect the controllers using a shared budget encoding and leverage a differentiable latency estimator for end-to-end training. This design enables SmartVL to learn cross-stage allocation strategies that adapt to both input complexity and runtime compute constraints. Experiments across multiple MLLM benchmarks demonstrate that, with joint scheduling, SmartVL consistently outperforms prior adaptive methods and achieves superior accuracy-efficiency Pareto frontiers. Project page: https://www.schaterji.io/publications/2026/jointtokencompute.

Pengcheng Wang, Zhiquan Wang, Jayoung Lee +5

Purdue University, West Lafayette, IN, USA · University of Wisconsin–Madison, Madison, WI, USA · NVIDIA, Santa Clara, CA, USA

Efficient Multimodal Inference Efficient VLM Inference Multimodal Large Language Models Multimodal Foundation Models Visual Token Pruning Adaptive Computation

Jul 22, 2026cs.CV

Multimodal Large Language Models for Remote Sensing Image Understanding: Domain-Specific or General-Purpose?

The rapid development of multimodal large language models (MLLMs) has introduced a flexible paradigm for remote sensing image scene understanding (RSISU), enabling natural-language interaction with remote sensing imagery. However, a systematic understanding of the capability boundaries, cross-task generalization, and task-specific limitations of existing remote sensing MLLMs (RS-MLLMs) is still lacking. This paper presents a systematic survey and diagnostic evaluation of MLLMs for RSISU. We review the technical evolution of RS-MLLMs, focusing on model design, multimodal learning, training data, and downstream capabilities. We further compare RS-MLLMs with general-purpose computer vision MLLMs (CV-MLLMs) across diverse RSISU tasks and benchmarks. RS-MLLMs remain competitive in domain-specific settings, particularly remote sensing visual grounding and high-resolution visual question answering. More notably, general-purpose CV-MLLMs can match or even outperform these specialized models on several RSISU tasks without remote sensing-specific fine-tuning. These findings demonstrate the strong transferability of general-purpose CV-MLLMs and show that current RS-MLLMs do not consistently outperform them across diverse RSISU tasks. Current MLLMs also face limitations in spatial and relational reasoning, fine-grained visual understanding, instruction diversity, and generalization across heterogeneous task formats. Based on these findings, we outline future directions toward reliable evaluation, multimodal and high-resolution reasoning, efficient deployment, and tool-augmented remote sensing agents. This survey provides a systematic reference for developing robust, generalizable, and practical MLLMs for RSISU.

Qiwei Ma, Chunping Qiu, Xinjun Cheng +5

School of Artificial Intelligence and Robotics, Hunan University, Changsha, 410082, China · Intelligent Game and Decision Lab (IGDL), Beijing, 100091, China · cYuelushan Center for Industrial Innovation, Changsha, 410082, China

Remote Sensing Image Understanding Remote Sensing VQA Multimodal Large Language Models Multimodal Model Evaluation Remote Sensing Visual Grounding

Jul 21, 2026cs.SD

RIME: Enabling Large-Scale Agentic Music Post-Production

Almost every piece of recorded music you have ever heard was modified before it reached you; commercial releases rarely spring fully formed from a musician's mind. Despite the promise of music generation models for one-shot output, such fine-grained iterative refinement workflows are a complementary problem and largely out of their reach. There is also a gap for musicians: while they can express what they want to hear, not all have the facility with studio production tools to implement the complex set of actions needed to realize these intuitions. We formalize this task as agentic post-production, wherein individual aspects of a track are targeted, refined, and combined into a final version. We argue the bottleneck is data: existing corpora do not reflect how realistic post-production chains map onto the vocabulary musicians and engineers actually use. We observe that there is a language for modifying recorded music that is dense, consistent, and learnable. To leverage this, we introduce the Rule-based Instructions for Music Editing (RIME) framework, which generates realistic paired edit-instruction data from any baseline music dataset grounded in canonical methods, design patterns, and constraints derived from real production workflows. RIME leverages POEMS, a toolkit that combines stem separation, mixing, and common studio effects for use by multimodal agents. We use POEMS and RIME to generate 15,000 pairs of edit instructions and ground-truth audio, then use this data to evaluate existing multimodal LLMs as agents on this task, revealing persistent limitations in current models. We also demonstrate RIME's ability to improve post-production agent performance via supervised fine-tuning on synthetic data. We see RIME as a step towards iterative musical agents, collaborative systems that could transform music production much as interactive coding agents have reshaped software engineering.

Noah Schaffer, Nikhil Singh

Dartmouth College

Audio Editing Multimodal Large Language Models Synthetic Data Generation for Language Models

Jul 21, 2026cs.CV

OmniReasoner: Thinking with Long Audio-Video via Native Tool Use

Long audio-video reasoning is difficult for omnimodal LLMs because the decisive evidence is often sparse, cross-modal, and too expensive to preserve with uniformly high-fidelity inputs. We introduce OmniReasoner, a tool-use post-training framework for Thinking with Long Audio-Video: omni-modal LLMs learn, via supervised fine-tuning and reinforcement learning, to decide whether and where to call a zoom-in tool before answering. OmniReasoner first builds a low-cost global preview of the full stream and then, when needed, calls the zoom-in tool with a requested temporal interval for higher-fidelity visual and audio inspection before answering. Because the model observes different sampling granularities before and after this call -- a sparse global preview and a denser local clip -- we introduce TimeAnchor, which keeps the tool's temporal argument valid and round-trip-consistent across these granularities, rather than tied to frame indices from a particular sampling rate. To make this tool-use behavior trainable without expensive manual interval annotation, we build a Temporal Augmented Data Engine that synthesizes tool-use post-training trajectories by video editing and composition. Experiments across omnimodal and video benchmarks show that OmniReasoner improves both answer accuracy and temporal grounding while concentrating high-fidelity computation on informative regions. Code is available at https://github.com/RockyChen0205/OmniReasoner.

Yu Chen, Caorui Li, Ziyu Xiong +8

University of Chinese Academy of Sciences · Institute of Automation, CAS · Southeast University +3

Temporal Video Grounding Audio-Visual Understanding Efficient Multimodal Inference Tool Use in VLMs Multimodal Large Language Models Multimodal Foundation Models

Jul 21, 2026cs.CL

MeetingToM: Evaluating Multimodal LLMs on Theory-of-Mind Reasoning in Multi-Party Meetings

Theory of Mind (ToM), the ability to infer other's beliefs, intentions, and states of knowledge, is central to social interaction, yet remains challenging for current Multimodal Large Language Models (MLLMs), especially in multi-party meetings where cues are distributed across speech and behavior. Existing multimodal ToM benchmarks mainly focus on video-grounded question answering over overt, externally verifiable signals, and provide limited coverage of latent social states and group dynamics. We introduce MeetingToM, a benchmark for complex social behavior reasoning in naturalistic multi-party meetings. MeetingToM targets meeting-specific phenomena such as \textbf{pseudo-consensus}, where apparent agreement masks private dissent under social pressure. The benchmark is hierarchically organized to evaluate ToM at increasing levels of social granularity, including (i) subject-level mental state prediction, (ii) dyadic-level addressee understanding, and (iii) group-level consensus reasoning. We provide a unified evaluation protocol and conduct systematic analyses of representative MLLMs, revealing persistent limitations in integrating non-verbal cues, inferring hidden attitudes, and distinguishing genuine consensus from pseudo-consensus. Our results highlight key challenges and establish MeetingToM as a testbed for advancing meeting-grounded ToM in multimodal models.

Ziyi Wang, Yuhang Wu, Dongxu Piao +3

College of AI, Tsinghua University · Department of Biostatistics and Bioinformatics, Duke University

Theory of Mind Multimodal Large Language Models Multimodal Model Evaluation

Jul 21, 2026cs.CL

Computational Humor with Multimodal LLMs: Methods, Datasets, Evaluation, and Challenges

Multimodal humor in memes, cartoons, and comics remains difficult for AI systems because intended meaning depends on non-literal mechanisms, shared cultural knowledge, and communicative intent rather than literal scene description. This survey focuses on visual humor understanding in single-image and multi-panel artifacts, while treating humor generation as an emerging downstream frontier. We position the literature against prior humor, sarcasm, and general MLLM surveys and organize it using a capability-centric hierarchy spanning recognition, interpretation and reasoning, and generation. Under this lens, we synthesize benchmark design, evaluation protocols, and modeling paradigms, tracing the field's shift from task-specific fusion models to large-model approaches based on multimodal alignment, evidence-grounded reasoning, and controlled generation. We conclude by highlighting the main barriers to progress: shortcut-prone evaluation, limited cultural and narrative coverage, weak evidence grounding, and unresolved safety and ownership concerns.

Tuo Liang, Zhe Hu, Disheng Liu +2

Case Western Reserve University · The Hong Kong Polytechnic University

Multimodal Large Language Models Computational Creativity Multimodal Model Evaluation

Jul 21, 2026cs.CV

In-Context Learning for Wound Classification with Small Multimodal Language Models

Wound image classification is often treated as a task-specific supervised learning problem, requiring substantial amounts of manually labelled data and retraining when the label space or deployment setting changes. This study evaluated whether small multimodal language models (SMLMs) can provide a training-free alternative for wound classification through retrieval-based in-context learning (ICL). Experiments used two public wound-image datasets: the Kaggle wound dataset (1469 images, 10 classes) and the Medetec dataset (560 images, 9 classes). Eleven SMLMs from the Qwen 3.5, Ministral 3, and Gemma 4 families were evaluated under zero-shot prompting and few-shot prompting with random support examples, embedding-based k-nearest-neighbour (kNN) retrieval, and kNN retrieval followed by maximal marginal relevance reranking (MMR). Retrieval-only weighted-kNN controls, support-set reduction experiments, and support-context size sweeps were used to assess the effects of retrieval, model scale, and prompt length. Query-conditioned ICL consistently outperformed zero-shot and random few-shot prompting. On the Kaggle dataset, the best result was achieved by Qwen 3.5 27B with kNN+MMR, reaching 0.872 accuracy and 0.871 F1 score. On Medetec, Qwen 3.5 27B with kNN+MMR reached 0.678 accuracy and 0.670 F1. Larger models exceeded matched weighted-kNN controls, indicating use of retrieved examples beyond nearest-neighbour voting. Retrieval-based ICL degraded modestly under support-set reduction, and most gains saturated with 8-10 support images. Retrieval-based ICL allows SMLMs to perform adaptable wound image classification without task-specific retraining. Compact retrieved contexts may support practical and privacy-conscious deployment, although performance remains dependent on model scale, retrieval strategy, and dataset difficulty.

George Martvel, Oskar Gustafsson, John Pavia +1

1Jönköping University, Jönköping, Sweden · 2Halmstad University, Halmstad, Sweden · 3Mölnlycke Health Care +1

Multimodal ICL Multimodal Large Language Models Medical Image Classification In-Context Learning Retrieval-Augmented ICL

Jul 20, 2026cs.HC

Querying Multimodal Scientific Papers with AI: Practices and Preferences Across Blind, Low-Vision, and Sighted Scientists

Visual diagrams, figures, and tables are central to scientific papers, and convey information beyond what is captured in text. While blind or low-vision (BLV) scientists have traditionally relied on static alternative text to access figures in papers, the rise of artificial intelligence (AI) has made interactive question-answering (QA) a feasible paradigm for visual exploration; yet little is known about how scientists use visual QA in practice or how to improve its accessibility. In this work, we interview five BLV and five sighted scientists across different STEM fields to understand how they use two AI tools, ChatGPT and Gemini, to query multimodal scientific documents. Our findings characterize how scientists review multimodal content, including existing practices (along with accessibility workarounds) for engaging with visuals, and feedback on the suitability of AI-generated responses to multimodal queries. We further find that vague or incomplete image descriptions, as well as incorrect AI outputs more broadly, can cause both BLV and sighted scientists to abandon AI workflows. To support future research, we additionally contribute a dataset of 115 queries and responses from our participants' interactions with the AI tools for papers in their field. We close by discussing implications for AI-powered scientific QA systems, emphasizing considerations for access across abilities and domains.

Arnavi Chheda-Kothary, Lucy Lu Wang, Joseph Chee Chang +1

Paul G. Allen School of Computer Science & Engineering University of Washington Seattle, WA, USA · Allen Institute for AI · The Information School University of Washington Allen Institute for AI Seattle, WA, USA +1

Multimodal Large Language Models Scientific QA Multimodal QA Human-AI Interaction

Jul 20, 2026cs.CV

HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization

Video understanding has become more and more important with the growth of Artificial Intelligence (AI) for video generation. Recently, Multimodal Large Language Model(M-LLM) has shown its capability in video understanding. Video summarization, a specific domain of video understanding, has proven its importance for efficient navigation and retrieval. Both video understanding and video summarization require a good selection of key frames in a video. Current video summarization methods heavily focus on the selected key frames and correlated segment captions. However, existing approaches overlook the perspective of treating the importance of the frames globally. We argue that using discrete selected frames for summarization will not only reduce the understanding coherence, but also lost important information in the video, as well as wasting the original capacity of the MLLMs. In this paper, we propose HAS, a Highlight-guided Attention Steering method for video summarization. We consider a challenging but practical setting where the video given to MLLMs for summarize should be continuous but with highlight guidance. HAS mainly consists of two parts: The first part is to find a continuous frame-level highlight distribution for the video globally. The second part is to apply the highlight distribution as an attention steering vector for the MLLM, targeting a better understanding of the video, and thus during the model inference time, putting more attention on the highlighted frames, while avoiding lost entire information on less highlighted frames through putting less attention instead of forgetting them. We evaluated HAS on a variety of benchmarks, and it has shown convincing performance in video summarization.

Rui Chu, Yingjie Lao

Tufts University, Medford, MA, USA

Video Summarization Multimodal Large Language Models Temporal Video Understanding

Jul 20, 2026cs.AI

PGN: Design and Implementation of a Vision-Language Navigation System Based on Pangu Multimodal Foundation Model

Vision-Language Navigation (VLN) requires an embodied agent to interpret a natural-language instruction and predict actions from temporally ordered visual observations. Adapting a multimodal large language model to VLN requires visual-language alignment, compact temporal inputs, action-space grounding, and stable training on the target hardware. This technical report presents PGN (Pangu Navigator), an offline VLN action-prediction system built on OpenPangu-7B. Training proceeds in two stages. First, PGMM aligns a frozen EVA-ViT-G/14 vision encoder with the frozen language backbone by training a Q-Former and a two-layer MLP projector. Second, PGN adapts the aligned model to expert navigation trajectories using five-observation windows, epoch-dependent temporal sampling, and a reasoning-then-action output format; this stage freezes the aligned visual pathway and updates three structural-token embeddings and LoRA adapters. The implementation combines mixed-precision computation, selective FP32 computation, and DeepSpeed ZeRO-2 on eight Ascend 910B NPUs. Under teacher-forced, open-loop evaluation on 500 held-out expert trajectories, V9 reports a 62.29% Normalized Action Match (NAM) and a 100.00% Non-empty Rate (NER). These metrics quantify offline expert-action alignment rather than closed-loop navigation success; evaluating error accumulation, path efficiency, and goal completion remains future work.

Li Xian, Mingxi Li, Yizheng Wang +3

School of Information and Communication Engineering University of Electronic Science and Technology of China

VLM Adaptation Multimodal Large Language Models Vision-Language Navigation

Jul 20, 2026cs.AI

Pailitao-MMSearch: Building Native E-Commerce Multimodal Search Foundation

The evolution of e-commerce has fundamentally transformed how users search for products, shifting from simple text-based keyword queries to complex multimodal interactions that seamlessly combine product images, natural language descriptions, and mixed-intent instructions. However, existing approaches face a critical dilemma: single-modal specialist models, deployed independently for text retrieval, visual search, and voice recognition, operate in isolation and cannot handle cross-modal queries, while general-purpose vision-language models lack the domain-specific knowledge necessary for fine-grained product understanding, user behavior modeling, and commercial intent reasoning. In this work, we present Pailitao-MMSearch, one native e-commerce multimodal search foundation model designed to bridge this gap. Our approach introduces three key innovations: (1)HybSID (Hybrid Semantic ID);(2)a two-stage continual pre-training strategy; and (3)a hybrid reasoning post-training pipeline. Built upon Qwen and deployed on Taobao's Pailitao multimodal search platform, Pailitao-MMSearch achieves substantial improvements in online A/B testing, including up to +13.61% in Gross Merchandise Volume (GMV) and +8.21% in transaction volume compared to traditional multi-modal search pipeline, demonstrating the effectiveness of our native e-commerce multimodal search large language models.

Xiaohan Ye, Xu Chen, Zihan Gong +15

Taobao & Tmall Group of Alibaba

Multimodal IR Multimodal Pretraining E-Commerce Search Multimodal Large Language Models Multimodal Reasoning

Jul 19, 2026cs.CV

TimeLens2: Generalist Video Temporal Grounding with Multimodal LLMs

Video multimodal large language models (MLLMs) can describe what happens in a video, but rarely identify when the supporting evidence occurs. We study generalist video temporal grounding, in which one model predicts a variable-cardinality set of evidence intervals across video lengths, domains, query forms, and viewpoints. Existing training strategies are misaligned with this set-valued task: long-video labels often rely on brittle one-pass annotation, while reinforcement-learning rewards either fail to distinguish non-overlapping predictions or require fragile segment matching. TimeLens2 treats temporal evidence as an interval set throughout supervision and optimization. TimeLens2-93K constructs reliable multi-span supervision through caption-derived proposals, independent localization, cross-agent consensus, semantic verification, and boundary refinement. Our temporal Wasserstein reward computes exact one-dimensional

W_1

between uniform distributions over merged interval supports, providing dense, matching-free feedback under unequal cardinalities and equivalent fragmentation; temporal IoU complements it with precise-overlap feedback. Across seven benchmarks, TimeLens2-2B outperforms all size-matched baselines on every benchmark, while the 4B and 8B variants achieve state-of-the-art performance, surpassing open-source models with up to 397B parameters. The 2B, 4B, and 8B variants improve over their Qwen3-VL backbones by 14.2, 13.0, and 18.1 mIoU points, respectively.

Yuhan Zhu, Changlian Ma, Xiangyu Zeng +12

Nanjing University · Shanghai AI Laboratory · Shanghai Jiao Tong University +3

Temporal Video Grounding Reinforcement Learning Multimodal Large Language Models Multimodal Foundation Models

Jul 19, 2026cs.CV

SkyVLaM: Multimodal Large Language Model for UAV Video Understanding in Remote Sensing

Recent advances in Multimodal Large Language Models (MLLMs) have significantly improved remote sensing (RS) multimodal understanding. Language-conditioned segmentation is crucial for fine-grained target understanding in Unmanned Aerial Vehicle (UAV) videos. However, this task remains challenging due to the prevalence of small, visually ambiguous targets and dynamic aerial perspectives. In this paper, we propose SkyVLaM, a multimodal large language model for UAV video understanding. SkyVLaM constructs sparse tokens directly from patch-level video representations through a temporal basis perceiver, regularizes the sparse basis to encourage complementary temporal cues, and adaptively selects a temporally coherent dense segment for high-resolution inspection. The resulting sparse and dense tokens are jointly processed by a large language model for query-conditioned segmentation. We further build SkyVid, consisting of SkyVid-VGCG and SkyVid-RVOS for video grounded conversation generation and referring video object segmentation, respectively. SkyVid contains 101 videos, 33.6K frames, and 1.53M pixel-level object instances. Experiments show that SkyVLaM provides a more effective allocation of the visual token budget and improves language-conditioned video segmentation in UAV scenarios.

Kaiwen Jing, Ruixu Jia, Bingyao Li +3

Beijing University of Posts and Telecommunications, Beijing, China · Peking University, Beijing, China · Beijing Wuzi University, Beijing, China

Referring Video Object Segmentation Multimodal Large Language Models UAV Remote Sensing Visual Token Compression

Jul 18, 2026cs.CV

Multi-Dimensional Quality Assessment for AI-Generated Human-Centric Videos: Dataset and Model

AI-generated human-centric videos play a crucial role in a wide range of modern applications. However, they often suffer from quality issues and semantic mismatches, underscoring the importance of effective quality assessment for such videos. To this end, we extend our previous dataset HVEval with pairwise preference annotations, resulting in HVEval+, the largest holistic quality assessment dataset for AI-generated human-centric videos, which comprises 1k prompts based on a comprehensive taxonomy, 20k videos generated by 24 text-to-video (T2V) models, and extensive human annotations, including 60k mean opinion scores (MOSs) and 60k preference pairs across 3 dimensions (i.e., spatial quality, temporal quality, and text-video correspondence), as well as 20k category-specific question-answer (Q&A) pairs. Along with the HVEval+ dataset, we further propose MoE-Rater, a Mixture-of-Experts (MoE)-inspired and multimodal large language model (MLLM)-based all-in-one method that supports multi-dimensional quality rating, multi-dimensional pairwise comparison, and category-specific question answering within a single model. Specifically, we introduce Mixture of Projector Experts (MoPE) and Mixture of LoRA Experts (MoLE), together with a three-stage training strategy consisting of task-aware pre-training, task-specific adaptation, and adaptive routing optimization, to effectively unify multiple tasks, resulting in superior performance on both HVEval+ and Human-AGVQA datasets. Extensive experiments and comprehensive analysis demonstrate the significant potential of the HVEval+ dataset and the MoE-Rater method in advancing AI-generated video quality assessment and further facilitating the evaluation and optimization of T2V models.

Sijing Wu, Yunhao Li, Huiyu Duan +4

Institute of Image Communication and Network Engineering, Shanghai Jiao Tong University, Shanghai, China · USC-SJTU Institute of Cultural and Creative Industry, Shanghai Jiao Tong University, Shanghai, China · Polytech Nantes, Universit´e de Nantes, France

Mixture of Experts Multimodal Large Language Models Video Quality Assessment Video Generation Evaluation

Jul 18, 2026cs.CV

Can Multimodal Large Language Models Understand OCT?

Optical coherence tomography (OCT) imaging is essential for the diagnosis and treatment of retinal diseases. Although multimodal large language models (MLLMs) have demonstrated considerable potential in medical image analysis, existing benchmarks largely reduce OCT understanding to coarse-grained disease classification or isolated visual question answering, leaving the complete cognitive process from visual perception to clinical reasoning insufficiently evaluated. To address this limitation, we introduce OCT-Bench, a comprehensive benchmark dedicated to OCT image understanding. OCT-Bench comprises 10,076 high-quality multiple-choice questions constructed from 4,137 OCT images across seven public datasets. Following the real-world clinical interpretation workflow, we establish a hierarchical capability taxonomy consisting of 20 fine-grained tasks across three dimensions: Perception, Cognition, and Reasoning. These tasks cover a broad range of capabilities, including imaging attributes, retinal anatomy, lesion characteristics, spatial relationships, disease assessment, therapeutic decision-making, and prognostic management. We systematically evaluate 20 representative MLLMs, including proprietary models, open-source general-purpose models, and medical-domain models. Experimental results demonstrate that current models remain substantially short of reliable OCT understanding. Moreover, neither medical-domain adaptation nor increased model scale consistently improves performance across capability levels. OCT-Bench enables comprehensive and fine-grained evaluation of MLLMs, providing a foundation for identifying capability bottlenecks and advancing clinically grounded OCT understanding.

Baochen Fu, Wenzhi Deng, Baihao Jin +5

1Shandong University · 4Shandong Provincial Qianfoshan Hospital · University of Science and Technology of China +2

Medical Imaging Medical Image Analysis Multimodal Large Language Models Medical VQA Optical Coherence Tomography Multimodal Model Evaluation+1

Jul 17, 2026cs.CV

Geometry-Enhanced Portion Estimation for Multimodal LLMs

Image-based dietary assessment promises to replace costly, bias-prone manual recalls, but portion estimation remains a major blocker. Multimodal LLMs (MLLMs) recognize a wide range of foods zero-shot in uncontrolled photos, yet they are weak at portion estimation -- a gap we measure across the current frontier (Gemini, GPT, and Claude flagships alike). We present a method that enhances a frozen, commercial MLLM with an accurate portion head: a small geometry-enhanced network on a frozen DINOv2 backbone with a structured softmax-ownership volume, consuming the MLLM's per-food name, bounding box, and density range -- no depth sensor, no MLLM fine-tuning. Evaluated fully open-vocabulary on three real-world benchmarks, the head cuts per-food portion error by 33-41% relative to the MLLM alone, outperforms every flagship MLLM's direct estimates, and surpasses each benchmark's originally published image-only model at its own reported metric.

Lin Liao, Peng Li

Multimodal Large Language Models Multimodal Foundation Models

Jul 17, 2026cs.CV

Knowing the Self, Understanding the World: A Dual-Cognition Benchmark for UAV Spatio-temporal Reasoning with MLLMs

Multimodal large language models have achieved strong performance across diverse vision-language tasks, yet their capabilities in UAV scenarios remain insufficiently explored. Recent UAV-oriented benchmarks have begun to evaluate MLLMs in aerial scenarios, but they typically focus on scene understanding, event recognition, or navigation completion, rather than jointly assessing the dual-cognition capability required for UAV agents: reasoning about both the UAV's own state and the external environment in multiview spatio-temporal contexts. To address this gap, we present UAV-DualCog, a benchmark for aerial multiview spatio-temporal reasoning built on this dual-cognition perspective. UAV-DualCog includes both image and video tasks to jointly evaluate self-state and environment-state reasoning, while requiring spatial or temporal grounding beyond discrete answer prediction. We also develop an automated pipeline that constructs data from scene-level semantic point clouds, yielding a scalable benchmark with diverse scenes, hundreds of landmarks, and thousands of QA samples. Extensive evaluations show that current MLLMs remain far from reliable in UAV dual cognition. Self-state reasoning, viewpoint transformation, precise spatial grounding, and temporal interval localization are persistent bottlenecks, and additional validation with thinking/frontier models and a human baseline confirms that the benchmark is understandable to humans but challenging for existing models. We further construct UAV-DualCog-Train from disjoint scenes and show through a lightweight optimization probe that it provides useful structured supervision, suggesting its value not only as an evaluation benchmark but also as a data resource for advancing MLLM-based UAV agents. Project website and supplementary materials: https://uav-dualcog.lozumi.com

Like Liu, Zhengzheng Xu, Haitao He +3

Northwestern Polytechnical University Xi’an, Shaanxi, China

Multimodal Grounding Aerial Robotics Spatiotemporal Reasoning Multimodal Large Language Models Multimodal Model Evaluation

Jul 17, 2026cs.CV

An Exam for Active Observers

Human vision is a closed loop: gaze is continuously redirected by intermediate hypotheses rather than a single snapshot. Decades of psychophysics and cognitive science have argued that this active observation is essential for a wide range of tasks. Whether today's multimodal large language models (MLLMs) exercise active observation is an empirical question that current vision-language benchmarks do not answer. We introduce ActiveVision, a benchmark that makes active observation measurable for MLLMs, comprising 17 tasks across 3 categories. Tasks are designed to force repeated visual perception rather than a single static description. Frontier MLLMs collapse on ActiveVision: the highest-scoring model we evaluate, GPT-5.5 at the highest exposed reasoning-effort tier, solves only 10.6% of items and scores zero on 11 of the 17 tasks, and even Claude Fable 5, despite topping most reasoning and coding leaderboards, solves just 3.5%, far behind three human participants who average 96.1%. Furthermore, much of the gap persists even when models write and run their own vision code: such code is unreliable on realistic imagery, and catching its failures itself requires the active perception the models lack. Together, these results indicate that current MLLMs lack robust active visual observation, motivating architectures and training objectives that close the perception-reasoning loop.

Jiarui Zhang, Muzi Tao, Shangshang Wang +3

University of Southern California

VLM Evaluation Multimodal Large Language Models Active Visual Perception