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 4, 2026cs.CV

ViPo-MLLM: Visual-Pose Multimodal LLM for Gloss-Free Sign Language Translation

Gloss-free Sign Language Translation (SLT) translates sign language videos into spoken-language sentences without gloss annotations, avoiding costly labeling but requiring fine-grained modeling of hands, body, and facial cues. Existing methods often use single-modality or weakly fused features, limiting performance. We propose ViPo-MLLM, a framework that integrates spatio-temporal RGB and human pose features. Dedicated encoders model intra-modal dynamics and cross-modal attention captures long-range dependencies. The fused representation is conditioned with a structured prompt and processed by an LLM trained with contrastive and language modeling objectives. The proposed model was evaluated on the PHOENIX14T and CSL-Daily datasets and achieved new state-of-the-art results on both datasets. Moreover, the ViPo-MLLM model attained competitive performance compared to gloss-based recognition approaches, confirming the effectiveness of the proposed pose cues and cross-modal attention mechanisms.

Ahmed Abul Hasanaath, Bicheng Xu, Mir Rayat Imtiaz Hossain +2

King Fahd University of Petroleum and Minerals, Dhahran, KSA · University of British Columbia, Vancouver, Canada

Sign Language Translation Multimodal Large Language Models

Jul 3, 2026cs.CV

Responsibility Distribution Estimation in Ego-View Accident Videos with Multimodal Large Language Models

Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured crash records. However, such data sources are costly to deploy and maintain at large scale, and they cannot objectively capture what the driver was actually able to observe before the accident. In contrast, ego-view accident videos directly represent the driver's visual perspective, making them suitable for reasoning about avoidability and driver responsibility. In this paper, we introduce responsibility distribution estimation for ego-view traffic accident videos, a new task in which a model predicts the percentage of responsibility assigned to each involved agent. We construct an LLM-assisted responsibility annotation pipeline and fine-tune multimodal large language models under multiple input settings, including raw frames, segmentation-enhanced input, and textual descriptions. Experimental results establish a strong initial benchmark, demonstrating that multimodal LLMs can effectively perform this nuanced, constraint-based reasoning task. Our findings suggest that ego-centric accident videos provide a promising foundation for socially and legally meaningful multimodal reasoning beyond conventional accident classification and explanation tasks.

Ryosei Tamura, Andrew Shin

Keio University

Multimodal Large Language Models Egocentric Video Understanding Multimodal Reasoning

Jul 3, 2026cs.LG

OmniFocus: Query-Guided Modality-Balanced Token Compression for Omni-Modal Large Language Models

Omni modal large language models (OmniLLMs) have attracted wide attention for their ability to jointly process audio and video, but they generate large token sequences under audio-visual inputs, leading to substantial inference cost. Existing audio-visual token compression methods often rely on unimodal guidance, overlooking the temporal locality of query-relevant evidence in audio-visual inputs and implicitly assuming that the two modalities share a temporally aligned information density distribution. We propose \textbf{OmniFocus}, a training-free query-guided token compression method for OmniLLMs that performs independent importance estimation for video and audio, enabling a modality-symmetric compression design that preserves modality-specific salient evidence while maintaining audio-visual alignment, thereby mitigating the modality bias issue that can arise from unimodal-guided compression. Experiments on the Qwen2.5-Omni model family across four audio-visual benchmarks show that OmniFocus maintains strong compressed performance at low token retention ratios and outperforms existing baselines on several major benchmark scores at 25% token retention. On DailyOmni with Qwen2.5-Omni-7B at 25% token retention, OmniFocus maintains 59.40 accuracy while delivering up to 1.38

\times

prefill speedup relative to the full-token baseline, highlighting a favorable practical accuracy-efficiency trade-off.

Shijie Cao, Qingyu Zhang, Boxi Yu +6

School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · Chinese Information Processing Laboratory, Institute of Software, Chinese Academy of Sciences · University of Limerick +1

Efficient Multimodal Inference Multimodal Large Language Models Multimodal Token Compression Multimodal Foundation Models Multimodal Understanding

Jul 3, 2026cs.CV

GuideMe: Multi-Domain Task Guidance and Intervention in Streaming Video

While multimodal Large Language Models (MLLMs) excel at offline video understanding, an interesting question of how far they are from serving as a real-time procedural coach remains unknown. Such a role typically requires an MLLM to continuously monitor the execution, detect mistakes, and provide corrective guidance in a closed-loop interaction. In this paper, we construct GuideMe, the first multi-domain benchmark for streaming video that supports training and evaluation of MLLMs for closed-loop interactive task guidance. It comprises 2,458 videos spanning 223.7 hours across diverse domains (\eg, cooking, object manipulation, daily-life guidance, and fitness), with 47,775 interaction samples covering next-step instructions, completion feedback, error detection, and corrective guidance. To evaluate existing models on GuideMe, we design a three-component assessment framework to measure the capabilities of representative MLLMs, which consists of temporal-semantic bipartite matching for sequence-level alignment, behavioral classification for intervention timing, and LLM-as-a-Judge for content quality. Extensive experiments highlight a critical performance asymmetry: despite excelling at providing instructions, existing MLLMs consistently fail to identify execution errors and respond with corrective feedback. Code and data are released at https://fawnliu.github.io/project/guideme.

Fang Liu, Jinpeng Chen, Ke Xu +7

City University of Hong Kong · Huawei Research · University of Science and Technology of China +2

VLM Evaluation Streaming Video Understanding Multimodal Large Language Models

Jul 3, 2026cs.CV

CL-Anomaly: Layer-Adaptive Mixture-of-Experts with Multimodal Large Language Model for Continual Learning in Anomaly Detection

Multimodal Large Language Models (MLLMs) excel in diverse vision tasks, but full-parameter retraining is computationally expensive as real-world knowledge evolves. Existing continual learning methods often suffer from semantic entanglement in parameter spaces across tasks, impeding the continuous deployment of models. This challenge is especially pronounced in Anomaly Detection (AD), which exhibits triple heterogeneity across modalities, domains, and defect scale variability, significantly complicating multi-task knowledge transfer. In this paper, we propose CL-Anomaly, a parameter-efficient fine-tuning framework based on an isolation-sharing collaboration to enable continual learning for anomaly detection with MLLMs. We introduce the task-private expert PrivLoRA, which physically isolates task-specific subspaces in the parameter space to prevent semantic entanglement of anomaly knowledge in diverse scenarios. The Layer-Adaptive Shared Experts maintain cross-task representations within a unified feature space, enabling knowledge sharing between previous and new tasks. Furthermore, we propose a Layer-Adaptive Knowledge Transfer strategy that automatically selects and dynamically updates the layer-wise key shared experts of each task via a momentum-based mechanism, promoting effective knowledge transfer across related anomaly detection tasks. Extensive experiments across three continual learning scenarios for anomaly detection, including class-incremental, cross-domain, and cross-modal, demonstrate that CL-Anomaly outperforms state-of-the-art methods. Code is available at https://github.com/WenDongyp/CL-Anomaly.

Wen Dong, Zhao Wang, Shuangqing Zhang +5

Nanjing University, Nanjing, China · China Mobile Zijin Innovation Institute, Nanjing, China · Nanjing University of Science and Technology, Nanjing, China

Mixture of Experts Multimodal Large Language Models Multimodal Anomaly Detection Continual Learning for VLMs Parameter-Efficient Fine-Tuning Anomaly Detection

Jul 3, 2026cs.CV

Learning Taxonomic Trees with Hierarchical Representation Regularization for Large Multimodal Models

Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language. Despite their impressive capabilities, large multimodal models (LMMs) often lack taxonomic knowledge, leading to low hierarchical visual recognition (HVR) consistency. These models typically only rely on language modeling objectives during fine-tuning and lack explicit taxonomy-aware regularization. To address this, we propose Hierarchical Representation Regularization (

HiR^2

), a simple plug-and-play regularizer that improves hierarchical consistency in LMMs. Specifically, we introduce a semantic-aware visual tree construction framework that extracts coarse-to-fine visual features from intermediate LLM layers guided by textual cues. The regularizer combines two complementary objectives: a taxonomic entailment loss that enforces hierarchy via hyperbolic entailment cones in the Lorentz model, and a discriminative dispersive loss that promotes angular separation of semantically similar embeddings on the unit sphere without disturbing the radial hierarchical structure. Extensive experiments demonstrate that

HiR^2

effectively captures taxonomic structures across diverse LMMs and fine-tuning methods. Code is available at https://github.com/PKU-ICST-MIPL/HiR2_ICML2026.

Hulingxiao He, Zhi Tan, Yuxin Peng

Wangxuan Institute of Computer Technology, Peking University

Hierarchical Representation Learning Multimodal Large Language Models

Jul 3, 2026cs.CV

ProLaViT: Learning Progressive Latent Visual Thoughts in Structured Latent Space

Multimodal Large Language Models (MLLMs) have achieved remarkable progress but still struggle with complex visual reasoning tasks requiring multi-step perception and logical deduction. While explicit visual generation incurs prohibitive computational costs, existing latent approaches often rely on external experts or lack rigorous cognitive logic. In this paper, we introduce ProLaViT (Progressive Latent Visual Thought), a framework empowering MLLMs to perform structured visual derivation in the continuous latent space. Unlike works dependent on heterogeneous external models, ProLaViT leverages an endogenous self-distillation mechanism, utilizing the model's own visual encoder to supervise latent thoughts. To facilitate this, we construct a scalable programmatic synthesis pipeline enabling the model to internalize algorithmic precision without inference time tools. We design two reasoning paradigms: (1) Coarse-to-Fine Causal Chain for spatial tasks, guiding attention from global context to local targets. (2) Dialectical Reasoning Chain for logical tasks, incorporating counter-factual thinking for verification. Furthermore, we propose a Distance-Weighted Diversity Loss to impose topology-aware constraints, preventing feature degeneration by enforcing semantic distinctiveness. Extensive experiments demonstrate that ProLaViT outperforms baselines on vision-centric benchmarks, achieving superior accuracy and interpretability with high efficiency.

Peiming Li, Yifan Wang, Xiaotian Zhang +4

Basic Algorithm Center, PCG, Tencent · Zhejiang University · Peking University

Multimodal Large Language Models Latent Visual Reasoning VLM Reasoning Visually Grounded Reasoning

Jul 2, 2026cs.CL

Gemma 4 Technical Report

We introduce Gemma 4, a new generation of open-weight, natively multimodal language models in the Gemma model family. Designed to advance compute efficiency and reasoning, the Gemma 4 model suite features dense and Mixture-of-Experts architectures, ranging from 2.3B to 31B parameters. Alongside improved vision and audio encoders for all model sizes, we propose a unified, encoder-free architecture for our 12B model, which ingests raw audio and image patches. Furthermore, we integrate a thinking mode, enabling Gemma models to generate reasoning traces prior to responding. We improve inference speed, memory, and compute efficiency, as well as long-context abilities through critical design choices. Gemma 4 establishes a leap in performance across STEM, multimodal, and long-context benchmarks, and rivals larger, frontier open models in human-rated tasks.

Gemma Team, Sherif El Abd, Vaibhav Aggarwal +298

Efficient Multimodal Inference Unified Multimodal Models Long-Context Language Model Inference Multimodal Large Language Models Multimodal Reasoning Open-Weight Language Models+2

Jul 2, 2026cs.CV

K9-Bench: Evaluating Multimodal LLMs on Canine-Centric Videos

MLLMs have shown strong zero-shot capabilities across diverse inputs such as across images, video, audio, and text. A crucial, yet underexplored, application of these models lies in understanding and modeling animal-centric scenarios. As animals are integral to millions of households, benchmarking next-generation AI models on pet-focused tasks, ranging from recognizing distress signals to enabling responsive robotic companions, is essential for building AI systems that can work alongside us. We introduce K9-Bench, a novel benchmark focused on real-world domestic dog videos, specifically targeting canine action and interaction understanding via approximately 5000 question-answer pairs across 907 videos spanning 5 distinct task categories that test long-form, canine-centric multimodal reasoning in MLLMs. To create this dataset, we propose a scalable, VLM/LLM-powered data generation pipeline that automatically mines canine-centric videos from the web and curates QA pairs requiring fine-grained, multi-hop reasoning over canine actions and temporally extended interaction sequences. We implement bias mitigation strategies designed to eliminate biases introduced by VLMs during dataset curation. Through extensive experimentation, we find that frontier MLLMs exhibit limited zero-shot performance on canine-centric tasks: although state-of-the-art closed-source models outperform open-source counterparts, they still struggle with compositional reasoning over subtle posture and interaction cues spread over long horizons. We observe that generic chain-of-thought prompting provides only modest performance for such long-horizon reasoning. Beyond a novel dataset for canine activity analysis, K9-Bench provides a general-purpose dataset construction pipeline that can be adapted to other low-data domains for quantitative analysis. Our project website is available at: https://ogmenrobotics.github.io/K9Bench.

Khush Attarde, Yusuf Ali, Megha Thukral +3

Ogmen Robotics Inc., Massachusetts, USA · Georgia Institute of Technology, Atlanta, USA

Video Understanding Multimodal Large Language Models Video QA Long-Video Understanding Animal Behavior Analysis Multimodal Model Evaluation

Jul 2, 2026cs.CV

EAGLE-360: Embodied Active Global-to-Local Exploration in 360 $^\circ$

While Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in standard visual understanding, adapting them for active visual search in 360

^\circ

panoramic environments exposes fundamental limitations. Specifically, standard MLLMs struggle to effectively model inherent panoramic properties, such as severe polar distortion and continuous cylindrical topologies, which significantly degrades target detection accuracy. Consequently, existing panoramic search methods attempt to compensate by relying heavily on fragmented local viewpoints. Burdened by rigid initialization and a lack of global panoramic priors, these approaches suffer from myopic, inefficient exploration and struggle with robust error recovery when targets are out of view. To overcome these challenges, we propose EAGLE-360, a novel Embodied Active Global-to-Local Exploration framework. Rather than performing exhaustive local searches, EAGLE-360 leverages global priors to establish an initial holistic perspective, iteratively reasoning and progressively narrowing the search space. Architecturally, we adapt RoPE Rolling, a coordinate-shifting positional encoding mechanism, to seamlessly model the continuous topologies of panoramas. To facilitate this paradigm, we construct the large-scale EAGLE-360 dataset, comprising 14,000+ 4K panoramas and 70,000+ rounds of high-quality VQA dialogues. By employing a training pipeline that integrates Supervised Fine-Tuning (SFT) with Group Relative Policy Optimization (GRPO), we effectively elicit complex spatial reasoning and tool-calling capabilities. Extensive experiments demonstrate that EAGLE-360 establishes a new state-of-the-art for 360

^\circ

visual search, achieving nearly an 8-fold increase in accuracy over the base model while significantly enhancing exploration efficiency.

Jingtao Xu, Zizhuo Lin, Jianwen Sun +2

1Zhejiang University · 2Central China Normal University

Multimodal Large Language Models

Jul 2, 2026cs.AI

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

Multimodal large language models must adapt to evolving tasks and domains, yet continual improvement under bounded deployment footprint remains difficult because repeated parameter updates or growing replay stores can accumulate adaptation state over time. We study fixed-footprint continual adaptation: the deployed adaptation state is kept under a fixed memory budget, while the backbone model is left unchanged and task-specific updates are externalized. We propose InduceKV, a retrieval-based method that stores each selected training prefix as an attention-ready memory entry, consisting of a frozen retrieval key and compact layerwise key--value (KV) payloads that can be appended to the model's self-attention cache. Under a strict memory budget, InduceKV constructs a compact inducing set through bilevel selection: a lightweight calibration is fit for retrieval, while the selected memory balances current-task likelihood, anchor-based retention, and coverage in the frozen retrieval space. Across task-incremental instruction tuning, continual VQA, domain-incremental adaptation, and lifelong multimodal instruction tuning, InduceKV consistently improves over PEFT, MoE, replay, and prompt-retrieval baselines under matched memory budgets. We further report backbone-matched, stage-1 CoIN, compute-matched, and scalability diagnostics, showing that the gains are not due to a stronger backbone, replay alone, or an unbounded candidate pool.

Qianyu Chen, Ziteng Feng, Canran Xiao +1

1Nanyang Technological University · University of Science and Technology of China · 3Shenzhen Campus of Sun Yat-sen University

Continual Learning for LLMs Memory-Efficient Fine-Tuning Memory-Augmented Language Models VLM Adaptation KV Caching Multimodal Large Language Models+2

Jul 2, 2026cs.AI

Multimodal Knowledge Edit-Scoped Generalization for Online Recursive MLLM Editing

Online multimodal knowledge editing requires injecting a continual stream of visual-textual corrections into multimodal large language models (MLLMs) with bounded overhead and minimal disruption to unrelated behaviors. Existing editors mainly emphasize edit reliability and long-horizon stability, but rarely control the semantic boundary of each edit. Our pilot analyses of post-edit behaviors and internal neuronal activities reveal a scope gap behind reliable edits: instance-level success neither guarantees transfer to valid cross-modal variants nor prevents leakage to unrelated inputs, while edit-related cross-modal responses concentrate in deeper semantic layers. Therefore, we formulate Edit-Scoped Generalization, reframing online MLLM editing from merely correcting an instance to controlling the propagation boundary of each edit. To this end, we propose ScopeEdit, a scope-aware online editor that decomposes each update into a modality-local absorption branch and an evidence-gated shared generalization branch. The local branch supports stable edit absorption, whereas the shared branch enables cross-modal propagation only when visual and textual evidence are sufficiently aligned. Both branches perform scope-separated write geometries in orthogonal low-rank spaces and maintain branch-wise preconditioners via Sherman--Morrison recursions, yielding constant per-edit overhead. Extensive experiments across diverse benchmarks, long-horizon edit streams, MLLM backbones, real-world VLKEB scenarios, and complex vision-language architectures show that ScopeEdit consistently improves the trade-off between in-scope cross-modal transfer and out-of-scope locality, while preserving edit reliability, stability and online efficiency. Our code is available at https://github.com/lab-klc/ScopeEdit.

Siyuan Li, Youyuan Zhang, Ruitong Liu +2

Harbin Institute of Technology, Shenzhen, China · Peng Cheng Laboratory · Peking University +1

Knowledge Editing Multimodal Large Language Models Model Editing

Jul 1, 2026cs.CV

Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation

While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging supervision from larger teacher models, relying solely on output token distributions has proven insufficient for compressing Multimodal Large Language Models (MLLMs). Since output tokens are a byproduct of the model attending to visual inputs, prior works have explored explicitly distilling attention to provide a direct supervisory signal. While promising, the precise utility of which attention signals to distill remains under-explored. In this work, we challenge the conventional reliance on prompt-to-vision attention by revealing that downstream performance correlates strongly with response-to-vision attention similarity to the teacher, but negligibly with that of prompt-conditioned attention. Furthermore, we observe that attention distributions exhibit significant variance across individual tokens, indicating that a uniform distillation objective is suboptimal. To this end, we introduce Token-level Response-visual Attention Guidance (TRAG), a distillation objective that 1) shifts the focus to response-to-vision signals and 2) employs token-specific objectives by adaptively weighting the Kullback-Leibler divergence based on attention entropy, effectively guiding the student to mirror the teacher's precise visual focus. Extensive experimental results on multiple benchmarks demonstrate that TRAG significantly outperforms prior distillation baselines.

Jaehyun Jang, Eunseop Yoon, Hee Suk Yoon +3

Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea · University of Illinois Urbana-Champaign, Champaign, USA

Cross-Modal Knowledge Distillation VLM Distillation Multimodal Large Language Models Self-Supervised Knowledge Distillation Knowledge Distillation

Jul 1, 2026cs.CV

Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning

Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways that bridge the multimodal query and the final answer. However, this introduces a severe train-inference mismatch: a training-time posterior, conditioned on the ground-truth answer, can exploit answer-dependent shortcuts. Standard variational training then forces the inference-time prior to mimic a posterior that has access to information unavailable at test time, leading to poor performance. To address this, we propose Asymmetric Mutual Variational Learning (AMVL), a framework that resolves this mismatch via a bidirectional calibration objective. A forward KL divergence trains the target-agnostic prior to match the posterior, while a novel reverse KL divergence simultaneously regularizes the posterior, preventing it from collapsing into inference-incompatible regions and mitigating this ``answer leakage''. We provide theoretical analysis formalizing this leakage as prior contamination and prove that our dual-KL objective reduces it. We instantiate AMVL in a latent-integrated MLLM and show that it consistently outperforms strong discrete and latent-reasoning baselines, improving the average score on the complex BLINK benchmark by +10.83 and achieving gains of up to +32.00 on individual reasoning tasks, with analyses confirming improved latent-space stability.

Shijie Li, Yilin Gao, Siyuan Yang +7

Shanghai Jiao Tong University · Ant Group

Multimodal Large Language Models Latent Visual Reasoning Continuous Latent Reasoning Multimodal Foundation Models Variational Inference Latent Reasoning+1

Jul 1, 2026cs.CV

Wake up for Touch! Mask-isolated Tactile Alignment Learning in MLLMs

Touch supplies the physical grounding needed to perceive intrinsic material properties, such as friction and compliance, that vision alone often cannot resolve. Recent efforts for equipping multimodal LLMs with this tactile sense, however, expose a zero-sum trade-off: the limited parameter budget of compact models forces a choice between acquiring the new sensory modality and preserving the established vision-language reasoning. We present Splash, a mask-isolated tactile alignment learning framework for MLLMs. Splash quantifies the significance of each pretrained parameter, and partitions the parameter space into a dormant and critical subspace. While the frozen critical subspace acts as a stable anchor to safeguard general visual knowledge, Splash updates the isolated dormant subspace to internalize tactile alignment towards LLMs. This selective, non-destructive expansion effectively prevents catastrophic forgetting and ensures non-destructive modality expansion. Extensive experiments show that Splash effectively achieves tactile reasoning without additional inference overhead in the LLM part, demonstrating state-of-the-art performance on visuo-tactile benchmarks, including SSVTP, TVL, and TacQuad, while preserving its original general-purpose capabilities.

Yoonhyung Park, Minji Kim, Sungwon Moon +1

Division of Artificial Intelligence & Software, Ewha Womans University

Visuo-Tactile Representation Learning Multimodal Large Language Models Multimodal Foundation Models Continual Learning for VLMs Parameter-Efficient Fine-Tuning Multimodal Understanding

Jun 30, 2026cs.CV

Decompose, Compare, and Decide: Multimodal LLMs are Implicit Few-Shot Learners

Multimodal Large Language Models (MLLMs) have demonstrated remarkable abilities when analyzing images, yet translating these capabilities to few-shot image classification remains challenging. To bridge this gap, we present DeCoDe, a simple yet effective technique that enables off-the-shelf MLLMs to act as strong few-shot classifiers without any additional training. Our approach builds on the idea of few-shot classification as a set of pairwise image comparisons, decomposing the task into a set of binary decisions. Given a query image and a support image from a candidate class, the MLLM is prompted to decide whether the two images depict the same class. The logit corresponding to an affirmative response is then used as a similarity score to assign the query image to the most likely class. While this already yields good results, we show that providing additional high-level information, such as the data domain, to the model further improves performance. Our evaluation provides an extensive analysis of various inference variants on a suite of twelve datasets, six established and six newly curated few-shot benchmarks spanning across diverse domains. The results show that the proposed simple decomposition technique can turn off-the-shelf MLLMs into powerful few-shot learners, significantly outperforming current state-of-the-art few-shot methods on both standard and novel domains. Code is available at https://github.com/yunhanwang1105/DeCoDe.

Yunhan Wang, Eshika Khandelwal, Edson Araujo +3

Tuebingen AI Center, University of Tuebingen, Germany

Multimodal Large Language Models Few-Shot Prompting Multimodal Foundation Models Few-Shot Image Classification

Jun 30, 2026cs.LG

CoMet: Context and Multiplicity Decomposition for Multimodal Uncertainty Estimation

Uncertainty estimation has been a long-standing challenge in AI models; it amounts to "knowing what you don't know," and metacognition is notoriously difficult even for humans (cf. the Dunning-Kruger effect). Although it is still far from solved even in simpler classification systems, tackling it in multimodal large language models (MLLMs) is becoming increasingly important. Within MLLMs, uncertainty can stem from any of the diverse sources as well as from their relationships, and further can stem from the unbounded answers in the open-ended setting. To tackle the issues, we propose CoMet, an MLLM uncertainty estimation method by decomposing uncertainty into a context-specific term and a multiplicity-specific term. The former captures ambiguity induced by the given context (e.g., task or prompt), while the latter captures how many plausible answers determined by the context remain compatible with the given input. We train a lightweight post-hoc uncertainty module to estimate these quantities, which enables efficient uncertainty estimation without autoregressive answer generation or repeated sampling. Experiments on various open-ended multimodal benchmarks, hallucination detection, and multiple-choice visual question answering benchmarks show that CoMet consistently improves uncertainty estimation over existing baselines while remaining efficient in practice. Code is available at https://github.com/princetonvisualai/comet_uncertainty

Sanghyuk Chun, William Yang, Amaya Dharmasiri +1

Princeton University

Uncertainty Quantification Multimodal Large Language Models LLM Uncertainty Estimation Uncertainty Decomposition

Jun 30, 2026cs.CV

ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs

Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token sequences. Training-free visual token reduction provides an efficient solution. However, existing methods distort attention distributions, giving rise to a phenomenon we term Attention Logit Collapse. To address this issue, we propose ERA, an Entropy-guided visual token pruning framework with Rectified Attention for efficient MLLMs. Specifically, ERA comprises three crucial components: Dual-view Entropy Pruning (DEP), Bias-aware Token Recycling (BTR), and Logit-preserving Attention Rectification (LAR). First, DEP identifies representative anchor tokens by jointly modeling visual diversity and head-wise saliency. BTR then recycles pruned tokens into their corresponding anchors while estimating a cluster-level logit bias. Building upon this, LAR injects the estimated bias into attention logits, effectively rectifying the collapse induced by token reduction. Together, these components preserve visual evidence even under aggressive compression, enabling robust performance across single-image, multi-image, and video settings on a wide range of MLLMs. Beyond delivering practical acceleration, ERA establishes logit-preserving visual token pruning as a principled framework for efficient MLLMs, unifying theoretical foundation, algorithmic design, and practical deployment. The code is at https://github.com/924973292/ERA.

Yuhao Wang, Mu Qiao, Haiwen Diao +5

School of Future Technology, Dalian University of Technology, Dalian 116024, China · S-Lab, Nanyang Technological University, Singapore 639798 · OPPO Research Institute, Shenzhen 518000, China +1

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

Jun 30, 2026cs.CV

Attend, Transform, or Silence: Operator-Level Visual Skipping for Efficient Multimodal LLM Inference

Multimodal large language models (MLLMs) increasingly process long visual-token sequences, increasing the overall inference computation. Existing acceleration methods usually remove visual tokens or skip visual-token updates in entire layers, but these coarse strategies may discard fine-grained evidence or suppress useful operators together with redundant ones. In this paper, we study visual-token computation from an answer-observable perspective and find that late visual-token updates can remain large while having little effect on answer-token representations. Motivated by this answer-silent redundancy, we decompose each Transformer layer into attention and FFN operators and show that useful visual computation is often operator-dominant and layer-dependent. We propose an operator-level visual-token skipping framework that preserves the full visual-token sequence while selectively bypassing redundant attention, FFN, or both. Experiments across three MLLM architectures and 10 VQA benchmarks show that our method achieves strong efficiency-accuracy trade-offs, reducing \textbf{33.7%} TFLOPs on Qwen3-VL while retaining \textbf{99.5%} of the vanilla model performance.

Zhaoyang Luo, Runmin Dong, Miao Yang +4

Tsinghua Shenzhen International Graduate School, Shenzhen, China · Sun Yat-sen University, Zhuhai, China · Tsinghua University, Beijing, China +1

Efficient VLM Inference Multimodal Large Language Models Visual Token Pruning Multimodal Understanding

Jun 30, 2026cs.AI

Harnessing Textual Refusal Directions for Multimodal Safety

To improve safety in Large Language Models (LLMs) we can either perform post-training alignment or exploit refusal directions in the activation space. Both strategies are less feasible in Multimodal LLMs (MLLMs) as they require unsafe multimodal data, harder to collect than their unimodal counterpart. In this work, we relax this constraint and investigate whether textual refusal directions, extracted directly from the LLM backbone, generalize across modalities (i.e., image, video). Preliminary findings confirm this ability, though effectiveness is conditioned by layer selection, steering strength, and cross-modal alignment, with the latter causing safe multimodal inputs to be spuriously steered toward refusal. Building on this, we introduce Modality-Agnostic Refusal Steering (MARS), a light-weight training-free approach that injects multimodal safety without the need for multimodal safety data. MARS corrects modality misalignment via activation re-centering, adaptively scales steering strength within a geometrically defined trust region, and selects the optimal intervention layer, operating at the first generated token. Evaluated on five SOTA MLLMs across safety, utility, and video jailbreak benchmarks, MARS achieves consistent safety gains while preserving utility. These results reveal that safety-relevant structure is shared across modalities and that textual refusal directions are a powerful and underexplored foundation for multimodal alignment.

Moreno D'Incà, Nicu Sebe, Massimiliano Mancini

University of Trento

Language Model Safety Evaluation Multimodal Large Language Models Activation Steering

Jun 30, 2026cs.CV

UniCoder: Unified Visual-to-Code Generation via Symbolic Rewards and Reference-Guided Code Optimization

Visual-to-Code generation, which transforms scientific plots, vector graphics, and webpages into executable scripts, demands a level of pixel-precise alignment that standard Multimodal Large Language Models (MLLMs) fail to achieve through Supervised Fine-Tuning (SFT) alone. While Reinforcement Learning (RL) offers a theoretical pathway to bridge this gap, its application is hindered by two fundamental obstacles: (1) \textit{Reward Coarseness}, where semantic metrics like CLIP scores fail to penalize fine-grained element deviations, and (2) \textit{Exploration Stagnation}, where the sparse, heterogeneous code search space prevents the policy from bootstrapping valid trajectories. To overcome these limitations, we introduce UniCoder, a unified RL framework that integrates two novel mechanisms. First, we propose \textbf{Symbolic Attribute Alignment}, which employs a lightweight auxiliary LLM to parse generated code into discrete visual attributes (e.g., hex colors, coordinate limits), enabling dense, element-wise reward computation. Second, to escape local optima, we devise \textbf{Reference-Guided Code Optimization}, a strategy that dynamically injects ground-truth trajectories into low-performing rollout groups, transforming blind exploration into guided policy improvement. Extensive experiments on ChartMimic, UniSVG, Design2Code and ScreenBench benchmarks demonstrate that our 8B-parameter model not only surpasses all open-source baselines but also achieves state-of-the-art performance comparable to proprietary models, establishing a new paradigm for generalized visual-to-code synthesis.

Yaozhi Zheng, Yilei Jiang, Manyuan Zhang +5

The Chinese University of Hong Kong · Shanghai Artificial Intelligence Laboratory

RL for Code Generation Reinforcement Learning Reward Shaping Code Generation Multimodal Large Language Models

Jun 30, 2026cs.CV

MS-Resampler: Multi-Scope Visual Resampling for Efficient Multimodal LLMs

Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform dense visual features into a compact token sequence for language modeling. Most existing resamplers adopt a single, fixed aggregation scope via global cross-attention, which can blur fine-grained local evidence and limit the ability to capture both local details and global context within a fixed token budget. In this work, we propose MS-Resampler, a multi-scope visual resampling framework for MLLMs. MS-Resampler instantiates multiple scope-specific resamplers by injecting explicit spatial scope priors into the resampling attention, enabling each branch to aggregate visual information at a particular granularity from local to global. The outputs of these scope-specific resamplers are then adaptively fused to produce the final visual representations for language modeling. Extensive experiments on ten public multimodal benchmarks show that MS-Resampler consistently improves visual understanding and multimodal reasoning over conventional single-scope resamplers, while introducing only minimal computational overhead.

Zhongyang Li, Yaqian Li, Faming Fang +6

Li Auto Inc. · East China Normal University.

Multimodal Large Language Models Multimodal Fusion Visual Token Compression Multimodal Understanding

Jun 30, 2026cs.CV

Learning to Deny: Action Denial in Multimodal Large Language Models

Multimodal large language models (MLLMs) have rapidly advanced video understanding, achieving strong zero-shot and few-shot recognition across standard benchmarks. Yet their ability to deny an action by recognizing when an activity is not happening despite strong contextual cues remains largely unexplored. We introduce UCF101-AD, a large-scale benchmark consisting of paired Action-Presence and Action-Denial clips, designed to evaluate this capacity for denial. Each negative video in UCF101-AD preserves the same contextual and motion cues, including persons, objects, and locations, as its positive counterpart, but the defining action itself is explicitly absent. Evaluating 20 state-of-the-art MLLMs reveals a consistent failure: models that exceed 85% accuracy on the positive action classes collapse below 50% on their action-denial counterparts, indicating a strong inclination to affirm plausible actions rather than verify that they truly occur. This exposes a critical blind spot in modern video understanding: the inability to reason causally about whether a motion actually happens. To probe this issue, we explore a causal graph formulation, CausalAct, which expresses scene structure through natural-language prompts linking context, interaction, and motion. Incorporating such causal cues substantially reduces false positives, demonstrating that denial is a learnable reasoning skill. UCF101-AD provides a new lens for diagnosing and improving causal reasoning in multimodal models. Dataset and relevant code: https://github.com/raiyaan-abdullah/Learn-to-Deny.

Raiyaan Abdullah, Shehreen Azad, Yogesh Singh Rawat

Institute of Artificial Intelligence, University of Central Florida, USA

Multimodal Large Language Models Causal Reasoning in Videos Multimodal Model Evaluation Multimodal Understanding

Jun 29, 2026cs.CV

OmniCoT: A Benchmark for Global and Multi-Step Panoramic Reasoning

Multimodal Large Language Models (MLLMs) have demonstrated promising spatial reasoning capabilities, while these abilities remain underexplored in the emerging visual modality of panoramic imagery. The full 360°

\times

180° field of view of panoramas essentially supports complex global multi-step reasoning, which is also the fundamental advantage of panoramas in applications such as embodied intelligence. However, existing panoramic benchmarks largely focus on simplistic queries that rely on local cues or single-/few-step reasoning, thereby ignoring the fundamental advantage of panoramas and failing to fully exploit their potential. To address this gap, we introduce OmniCoT, a panoramic spatial reasoning suite designed to enable MLLMs to use global evidence and perform multi-step inference across viewpoints. It includes OmniCoT-B (6.7K data) for evaluation, which measures both answer accuracy and reasoning quality, OmniCoT-Real (1K data) as a manually annotated real-world subset to quantify the Sim-to-Real gap. For training, OmniCoT-T (14.3K data) is purpose-built with structured stepwise Chain-of-Thought annotations that explicitly link intermediate reasoning steps to panoramic evidence. Based on OmniCoT-T, we introduce OmniCoT-R1 and adopt a two-stage training strategy tailored to the geometrically complex panoramic space, where Supervised Fine-tuning (SFT) anchors reasoning to panoramic evidence (e.g., bearings, proximity) and GRPO penalizes geometrically incoherent paths to consolidate global 360° spatial consistency. Through OmniCoT, we aim to recalibrate the difficulty of panoramic spatial reasoning to better align with the intrinsic capabilities of panoramic imagery, thereby fostering meaningful progress in this research area.

Haocong He, Chenfei Liao, Zichen Wen +13

SJTU · HKUST(GZ) · Shanghai AI Lab +6

Visual Spatial Reasoning Multimodal Large Language Models Multimodal CoT Reasoning Multimodal Model Evaluation

Jun 29, 2026cs.CV

Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models

Multimodal large language models (MLLMs) often fail in fine-grained visual reasoning, as question-relevant visual cues are diluted by dense and redundant image tokens. Recent multimodal reasoning methods usually extend chain-of-thought from language models into visual or latent spaces, seeking to add intermediate reasoning states while overlooking the negative impact of redundant visual tokens. We propose LatEnt Noise maSk (Lens), a question-conditioned visual evidence purification framework that empowers MLLMs to reason with cleaner visual cues in latent space. Lens introduces a lightweight Lens Evidence Token (LET) to score which visual tokens support the current question and preserve them during decoding. Guided by the LET scores, it injects adaptive latent noise into low-relevance tokens, softly suppressing distractors without changing the model backbone or token sequence. With only one temporary learnable control token and a lightweight noise generator, Lens adds minimal overhead while improving the base MLLM by 2.4-6.4 points on most VQA datasets and by 4.1-6.4 points on grounding tasks. These results show that multimodal reasoning can benefit more directly from cleaner question-relevant visual evidence than from simply extending the reasoning trace.

Kai Jiang, Ruishu Zhu, Siqi Huang +2

School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University · Institute of Artificial Intelligence, China Telecom (TeleAI) · 3Fudan University +1

Visual Question Answering Multimodal Large Language Models VLM Reasoning Visually Grounded Reasoning Multimodal Understanding

Jun 29, 2026cs.CV

MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs

Audiovisual arts encompass diverse creative disciplines, including cinema, visual arts, stage performance, and game design, where artistic meaning arises from deliberate combinations of visual, auditory, and narrative elements (e.g., fear amplified through claustrophobic framing, or grief conveyed through silence and lingering close-ups). True artistic understanding extends beyond recognizing what is depicted to reasoning about why it is expressed through particular creative choices. Despite the strong progress of multimodal large language models (MLLMs), this critical aspect of artistic understanding remains underexplored, as existing benchmarks largely measure perceptual recognition while overlooking reasoning about creative intent. To address this gap, we introduce Musebench, a comprehensive benchmark designed to evaluate MLLMs on nuanced artistic understanding. It comprises 4,016 questions spanning cinematic arts, static visual arts, stage performing arts, and game arts, distilled from over 10K candidate video essays that pair professional commentary with visual demonstration. To capture the open-ended nature of artistic analysis at scale, the benchmark combines single-select and variable-option multi-select questions. All questions are generated and refined through a four-phase iterative pipeline combining shortcut filtering, adversarial distractors, and expert validation. Comprehensive zero-shot evaluation of 28 state-of-the-art MLLMs reveals that even the best-performing model achieves only 48.29% accuracy, substantially below human expert performance of 87.18%, exposing a significant gap in current models' creative domain expertise.

Yuxuan Fan, Gyusik Seo, Jing Hao +3

1NTU Singapore · 2The University of Hong Kong · 3Johns Hopkins University +2

Audio-Visual Understanding Multimodal Large Language Models Multimodal Model Evaluation

Jun 29, 2026cs.CV

Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal Reasoning

Inductive biases steer learning toward generalizable solutions by encoding task structure. In this work, we identify a crucial missing bias in MLLMs: cross-view consistency, \textit{i.e.}, semantically invariant views of the same instance should lead to the same answer. Standard reinforcement learning with verifiable rewards (RLVR) objectives do not impose this constraint, but instead assign pointwise rewards to each visual input. Even with data augmentation (DA), transformed views are typically rewarded independently, providing little signal once within-view rewards saturate. We propose \textbf{ConsistRoll}, a simple but effective method that injects cross-view consistency into RLVR training by reusing the group-sampling mechanism of GRPO. Specifically, ConsistRoll places original and semantically invariant transformed views in the same generation group, and assigns a joint reward only when paired completions are both correct and consistent. In this way, ConsistRoll turns consistency into an online credit-assignment signal, \textbf{without extra generation overhead and annotations}. Theoretically, we show that cross-view consistency is a valid inductive bias, and ConsistRoll introduces a cross-view correction term absent from DA, penalizing view dependence and alleviating advantage collapse. Comprehensive benchmarks across math, general-purpose, hallucination domains confirm that ConsistRoll achieves robust improvements in multimodal reasoning.

Xin Zou, Haolin Deng, Yibo Yan +6

HKUST (GZ) · HKUST · UIC +1

Multi-View Consistency Multimodal Robustness Multimodal Large Language Models Multimodal Reasoning Reinforcement Learning with Verifiable Rewards Multimodal Foundation Models+1

Jun 29, 2026cs.HC

Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework

Chart data extraction, which reverse-engineers data tables from chart images, is essential for reproducibility, analysis, retrieval, and redesign. Existing interactive tools are reliable but tedious, and mixed-initiative systems, while more efficient, lack generalizability. Recent multimodal large language models (MLLMs) offer a unified interface for chart interpretation, yet their ability to extract accurate data tables, especially without visible labels, remains unclear. We build a benchmark featuring diverse real-world charts without data labels to evaluate this capability. Results show that, while current MLLMs reliably reconstruct table structures, they struggle with precise value recovery. To address this, we revisit chart data extraction from a human-centered perspective and argue that extraction should follow a progressive learning process similar to how people read charts. Our training framework substantially improves numerical accuracy, achieving state-of-the-art performance with a 7B-parameter model. A user study further shows that our model effectively supports mixed-initiative workflows for reliable chart data extraction.

Yuchen He, Peizhi Ying, Liqi Cheng +4

State Key Lab of CAD&CG, Zhejiang University · Zhejiang University Hangzhou, Zhejiang, China · Guangdong University of Technology Guangzhou, Guangdong, China

Document Information Extraction Multimodal Large Language Models Chart Data Extraction Chart Understanding Multimodal Model Evaluation

Jun 29, 2026cs.CV

Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation

Multimodal Large Language Models (MLLMs) are prone to hallucination as their generation preferences are insufficiently calibrated to visual evidence, causing them to fall back on linguistic priors, rather than faithful grounding. In this work, we start from an empirical observation: when query-relevant visual evidence is explicitly strengthened using the model's own attention, generation becomes more accurate, suggesting that many failures do not arise solely from missing perception, but from an insufficient tendency to trust the evidence the model has already attended to. Motivated by this finding, we propose Oriented Pickup Preference Optimization (\texttt{OPPO}), an evidence-aware alignment objective that learns preferences over the strength of visual evidence, rather than only response quality. Concretely, \texttt{OPPO} contrasts the same faithful response under stronger, anchored, weaker-evidence views, turning naive visual preference into ordered visual-evidence alignment. We further combine this objective with fine-grained span-level and token-level regularization to stabilize the training. Besides, we provide a theoretical analysis showing that ordered evidence margins induce a positive lower bound on local visual sensitivity. Extensive evaluations across hallucination and general-purpose benchmarks demonstrate that \texttt{OPPO} consistently outperforms baseline methods.

Xin Zou, Haolin Deng, Yibo Yan +5

HKUST (GZ) · HKUST · OPPO AI Center

Multimodal Large Language Models Multimodal Hallucination Visually Grounded Reasoning Visual Grounding Multimodal Foundation Models VLM Hallucination Mitigation+1

Jun 29, 2026cs.CL

How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning

Evaluating the originality of visual images poses enduring challenges for creativity assessment. Automated scoring using AI models has proven effective in the verbal domain, yet key questions remain about evaluating visual creativity and understanding how models arrive at their ratings. The present research asks whether multimodal large language models (LLMs) can serve as judges of visual creativity zero-shot (without any fine-tuning or examples of human ratings) and whether their "reasoning" output offers an interpretable window into their evaluation process. We tested six multimodal LLMs (Gemini 3 Flash, Gemma 4 31B IT, GPT-5.4 Mini, GLM-5v Turbo, Kimi K2.5, and Qwen 3.6 Plus) on 992 AI-generated images (based on human-written prompts) and 1,500 hand-drawn sketches scored for creativity by human raters. In Study 1, all models showed substantial alignment with human creativity ratings on both datasets (r = .57-.68 on AI-generated images; r = .29-68 on sketches). In Study 2, we analyzed the step-by-step reasoning processes of three LLMs evaluating the same images and drawings. Although reasoning made model evaluations interpretable -- showing what they attend to, how they balance originality vs. quality, and how they justify their ratings -- reasoning did not improve alignment with human ratings. In sum, our findings indicate that multimodal LLMs can match human judgments of visual creativity without any additional training, and that their reasoning reveals how AI models evaluate creativity. An open scoring app implementing this pipeline is available at https://review-visual-eval-scoring.hf.space.

William Orwig, Roger E. Beaty

Harvard University, Department of Psychology, Cambridge, MA, USA · Pennsylvania State University, Department of Psychology, University Park, PA, USA

Creativity Assessment LLM-as-a-Judge Multimodal Large Language Models VLM Interpretability Computational Creativity