Multimodal Large Language Models

Also known as MLLM

Follow this topic Ask about this topic

Multimodal large language models connect language generation and reasoning to visual, audio, video, and sometimes sensor or structured data. Common approaches align pretrained modality encoders with a language model using projectors or adapters, or train models to process modalities jointly; instruction tuning, reinforcement learning, retrieval, and tool use extend their capabilities. Evaluation spans visual question answering, document reading, long-video and spatial reasoning, and specialized settings such as medical imaging, where models still often miss fine-grained evidence or fail to use it consistently. A central tension is how to improve cross-modal grounding, temporal and physical reasoning, and safety while reducing the high inference costs of processing long or detailed inputs.

Latest papers

1,096 papers106 papers in the last four weeks, up 23% on the four weeks before. 0.6% of all new papers.

Mar 5, 2026

On the Generalization Capacities of MLLMs for Spatial Intelligence

Multimodal Large Language Models (MLLMs) that directly process RGB inputs for tasks like 3D localization and navigation have shown remarkable potential. However, we argue that these RGB-only approaches are fundamentally flawed in their ability to generalize across cameras. By ignoring camera parameters, they entangle an object's physical properties with the camera's perspective, creating an irresolvable ambiguity. We show this leads MLLMs to overfit to the training camera distribution, rather than learning true and generalizable 3D geometric principles. To address this, we propose Camera-Aware MLLM framework for spatial MLLMs. It learns generalizable spatial reasoning by: (i) injecting camera intrinsics via a dense embedding that conditions each visual token; (ii) introducing a camera-aware data augmentation strategy that synthetically varies camera parameters, forcing the model to disentangle camera properties from scene content; and (iii) distilling geometric priors from a 3D vision foundation model. Extensive experiments demonstrate that camera-aware MLLMs substantially outperform their naive counterparts, particularly in cross-camera generalization tests on spatially-grounded tasks, indicating that camera-awareness is not only beneficial but also a prerequisite for robust and generalizable spatial intelligence in MLLMs.

Gongjie Zhang, Wenhao Li, Quanhao Qian +4

DAMO Academy, Alibaba Group · HuPan Lab · Nanyang Technological University

Multimodal Large Language Models 3D Spatial Reasoning

Mar 5, 2026

Mario: Multimodal Graph Reasoning with Large Language Models

Recent advances in large language models (LLMs) have opened new avenues for multimodal reasoning. Yet, most existing methods still rely on pretrained vision-language models (VLMs) to encode image-text pairs in isolation, ignoring the relational structure that real-world multimodal data naturally form. This motivates reasoning on multimodal graphs (MMGs), where each node has textual and visual attributes and edges provide structural cues. Enabling LLM-based reasoning on such heterogeneous multimodal signals while preserving graph topology introduces two key challenges: resolving weak cross-modal consistency and handling heterogeneous modality preference. To address this, we propose Mario, a unified framework that simultaneously resolves the two above challenges and enables effective LLM-based reasoning over MMGs. Mario consists of two innovative stages. Firstly, a graph-conditioned VLM design that jointly refines textual and visual features through fine-grained cross-modal contrastive learning guided by graph topology. Secondly, a modality-adaptive graph instruction tuning mechanism that organizes aligned multimodal features into graph-aware instruction views and employs a learnable router to surface, for each node and its neighborhood, the most informative modality configuration to the LLM. Extensive experiments across diverse MMG benchmarks demonstrate that Mario consistently outperforms state-of-the-art graph models in both supervised and zero-shot scenarios for node classification and link prediction. The code will be made available at https://github.com/sunyuanfu/Mario.

Yuanfu Sun, Kang Li, Pengkang Guo +2

New York University Shanghai · New York University · Tsinghua University +1

LLM Reasoning with Graphs Multimodal Reasoning Multimodal Graph Learning Multimodal Large Language Models

Mar 5, 2026

VisionPangu: A Compact and Fine-Grained Multimodal Assistant with 1.7B Parameters

Large Multimodal Models (LMMs) have achieved strong performance in vision-language understanding, yet many existing approaches rely on large-scale architectures and coarse supervision, which limits their ability to generate detailed image captions. In this work, we present VisionPangu, a compact 1.7B-parameter multimodal model designed to improve detailed image captioning through efficient multimodal alignment and high-quality supervision. Our model combines an InternVL-derived vision encoder with the OpenPangu-Embedded language backbone via a lightweight MLP projector and adopts an instruction-tuning pipeline inspired by LLaVA. By incorporating dense human-authored descriptions from the DOCCI dataset, VisionPangu improves semantic coherence and descriptive richness without relying on aggressive model scaling. Experimental results demonstrate that compact multimodal models can achieve competitive performance while producing more structured and detailed captions. The code and model weights will be publicly available at https://www.modelscope.cn/models/asdfgh007/visionpangu.

Jiaxin Fan, Wenpo Song

National Key Laboratory for Novel Software Technology, Nanjing University

Vision-Language Models Multimodal Large Language Models Image Captioning Vision-Language Alignment

Mar 5, 2026

Multi-Paradigm Collaborative Adversarial Attack Against Multi-Modal Large Language Models

The rapid progress of Multi-Modal Large Language Models (MLLMs) has significantly advanced downstream applications. However, this progress also exposes serious transferable adversarial vulnerabilities. In general, existing adversarial attacks against MLLMs typically rely on surrogate models trained within a single learning paradigm and perform independent optimisation in their respective feature spaces. This straightforward setting naturally restricts the richness of feature representations, delivering limits on the search space and thus impeding the diversity of adversarial perturbations. To address this, we propose a novel Multi-Paradigm Collaborative Attack (MPCAttack) framework to boost the transferability of adversarial examples against MLLMs. In principle, MPCAttack aggregates semantic representations, from both visual images and language texts, to facilitate joint adversarial optimisation on the aggregated features through a Multi-Paradigm Collaborative Optimisation (MPCO) strategy. By performing contrastive matching on multi-paradigm features, MPCO adaptively balances the importance of different paradigm representations and guides the global perturbation optimisation, effectively alleviating the representation bias. Extensive experimental results on multiple benchmarks demonstrate the superiority of MPCAttack, indicating that our solution consistently outperforms state-of-the-art methods in both targeted and untargeted attacks on open-source and closed-source MLLMs. The code is released at https://github.com/LiYuanBoJNU/MPCAttack.

Yuanbo Li, Tianyang Xu, Cong Hu +3

School of Artificial Intelligence and Computer Science, Jiangnan University · Centre for Vision, Speech and Signal Processing (CVSSP), University of Surrey

Adversarial Attacks on Unified Multimodal Models Transfer-Based Adversarial Attacks Multimodal Large Language Models

Mar 5, 2026

MASQuant: Modality-Aware Smoothing Quantization for Multimodal Large Language Models

Post-training quantization (PTQ) with computational invariance for Large Language Models~(LLMs) have demonstrated remarkable advances, however, their application to Multimodal Large Language Models~(MLLMs) presents substantial challenges. In this paper, we analyze SmoothQuant as a case study and identify two critical issues: Smoothing Misalignment and Cross-Modal Computational Invariance. To address these issues, we propose Modality-Aware Smoothing Quantization (MASQuant), a novel framework that introduces (1) Modality-Aware Smoothing (MAS), which learns separate, modality-specific smoothing factors to prevent Smoothing Misalignment, and (2) Cross-Modal Compensation (CMC), which addresses Cross-modal Computational Invariance by using SVD whitening to transform multi-modal activation differences into low-rank forms, enabling unified quantization across modalities. MASQuant demonstrates stable quantization performance across both dual-modal and tri-modal MLLMs. Experimental results show that MASQuant is competitive among the state-of-the-art PTQ algorithms. Source code: https://github.com/alibaba/EfficientAI.

Lulu Hu, Wenhu Xiao, Xin Chen +4

Alibaba Cloud Computing, Alibaba Group

Post-Training Quantization Neural Network Quantization Multimodal Large Language Models

Mar 5, 2026

Are Multimodal LLMs Ready for Surveillance? A Reality Check on Zero-Shot Anomaly Detection in the Wild

Multimodal large language models (MLLMs) have demonstrated impressive general competence in video understanding, yet their reliability for real-world Video Anomaly Detection (VAD) remains largely unexplored. Unlike conventional pipelines relying on reconstruction or pose-based cues, MLLMs enable a paradigm shift: treating anomaly detection as a language-guided reasoning task. In this work, we systematically evaluate state-of-the-art MLLMs on the ShanghaiTech and CHAD benchmarks by reformulating VAD as a binary classification task under weak temporal supervision. We investigate how prompt specificity and temporal window lengths (1s--3s) influence performance, focusing on the precision--recall trade-off. Our findings reveal a pronounced conservative bias in zero-shot settings; while models exhibit high confidence, they disproportionately favor the 'normal' class, resulting in high precision but a recall collapse that limits practical utility. We demonstrate that class-specific instructions can significantly shift this decision boundary, improving the peak F1-score on ShanghaiTech from 0.09 to 0.64, yet recall remains a critical bottleneck. These results highlight a significant performance gap for MLLMs in noisy environments and provide a foundation for future work in recall-oriented prompting and model calibration for open-world surveillance, which demands complex video understanding and reasoning.

Shanle Yao, Armin Danesh Pazho, Narges Rashvand +1

Electrical and Computer Engineering Department, University of North Carolina at Charlotte, Charlotte, USA

Video Anomaly Detection Zero-Shot Anomaly Detection Multimodal Large Language Models Weakly Supervised Video Anomaly Detection Prompt Engineering

Mar 4, 2026

Visuospatial Perspective Taking in Multimodal Language Models

As multimodal language models (MLMs) are increasingly used in social and collaborative settings, it is crucial to evaluate their perspective-taking abilities. Existing benchmarks largely rely on text-based vignettes or static scene understanding, leaving visuospatial perspective-taking (VPT) underexplored. We adapt two evaluation tasks from human studies: the Director Task, assessing VPT in a referential communication paradigm, and the Rotating Figure Task, probing perspective-taking across angular disparities. Across tasks, MLMs show pronounced deficits in Level 2 VPT, which requires inhibiting one's own perspective to adopt another's. These results expose critical limitations in current MLMs' ability to represent and reason about alternative perspectives, with implications for their use in collaborative contexts.

Jonathan Prunty, Seraphina Zhang, Patrick Quinn +3

Leverhulme Centre for the Future of Intelligence, University of Cambridge · Department of Psychology, University of Cambridge · Microsoft Research Asia

Multimodal Large Language Models Visual Spatial Reasoning Multimodal Model Evaluation

Mar 3, 2026

Social Norm Reasoning in Multimodal Language Models: An Evaluation

In Multi-Agent Systems (MAS), agents are designed with social capabilities, allowing them to understand and reason about social concepts such as norms when interacting with others (e.g., inter-robot interactions). In Normative MAS (NorMAS), researchers study how norms develop, and how violations are detected and sanctioned. However, existing research in NorMAS use symbolic approaches (e.g., formal logic) for norm representation and reasoning whose application is limited to simplified environments. In contrast, Multimodal Large Language Models (MLLMs) present promising possibilities to develop software used by robots to identify and reason about norms in a wide variety of complex social situations embodied in text and images. However, prior work on norm reasoning have been limited to text-based scenarios. This paper investigates the norm reasoning competence of five MLLMs by evaluating their ability to answer norm-related questions based on thirty text-based and thirty image-based stories, and comparing their responses against humans. Our results show that MLLMs demonstrate superior performance in norm reasoning in text than in images. GPT-4o performs the best in both modalities offering the most promise for integration with MAS, followed by the free model Qwen-2.5VL. Additionally, all models find reasoning about complex norms challenging.

Oishik Chowdhury, Anushka Debnath, Bastin Tony Roy Savarimuthu

School of Computing, University of Otago, New Zealand

Social Reasoning Multimodal Large Language Models Multimodal Reasoning

Mar 3, 2026

MoD-DPO: Towards Mitigating Cross-modal Hallucinations in Omni LLMs using Modality Decoupled Preference Optimization

Omni-modal large language models (omni LLMs) have recently achieved strong performance across audiovisual understanding tasks, yet they remain highly susceptible to cross-modal hallucinations arising from spurious correlations and dominant language priors. In this work, we propose Modality-Decoupled Direct Preference Optimization (MoD-DPO), a simple and effective framework for improving modality grounding in omni LLMs. MoD-DPO introduces modality-aware regularization terms that explicitly enforce invariance to corruptions in irrelevant modalities and sensitivity to perturbations in relevant modalities, thereby reducing unintended cross-modal interactions. To further mitigate over-reliance on textual priors, we incorporate a language-prior debiasing penalty that discourages hallucination-prone text-only responses. Extensive experiments across multiple audiovisual hallucination benchmarks demonstrate that MoD-DPO consistently improves perception accuracy and hallucination resistance, outperforming previous preference optimization baselines under similar training budgets. Our findings underscore the importance of modality-faithful alignment and demonstrate a scalable path toward more reliable and resilient multimodal foundation models.

Ashutosh Chaubey, Jiacheng Pang, Mohammad Soleymani

University of Southern California

Multimodal Large Language Models Multimodal Hallucination Direct Preference Optimization

Mar 3, 2026

OCR or Not? Rethinking Document Information Extraction in the MLLMs Era with Real-World Large-Scale Datasets

Multimodal Large Language Models (MLLMs) enhance the potential of natural language processing. However, their actual impact on document information extraction remains unclear. In particular, it is unclear whether an MLLM-only pipeline--while simpler--can truly match the performance of traditional OCR+MLLM setups. In this paper, we conduct a large-scale benchmarking study that evaluates various out-of-the-box MLLMs on business-document information extraction. To examine and explore failure modes, we propose an automated hierarchical error analysis framework that leverages large language models (LLMs) to diagnose error patterns systematically. Our findings suggest that OCR may not be necessary for powerful MLLMs, as image-only input can achieve comparable performance to OCR-enhanced approaches. Moreover, we demonstrate that carefully designed schema, exemplars, and instructions can further enhance MLLMs performance. We hope this work can offer practical guidance and valuable insight for advancing document information extraction.

Jiyuan Shen, Peiyue Yuan, Atin Ghosh +2

SAP · Stanford University

Document Information Extraction Multimodal Large Language Models LLM Evaluation

Mar 3, 2026

Seeing Clearly without Training: Mitigating Hallucinations in Multimodal LLMs for Remote Sensing

Multimodal large language models (MLLMs) suffer from pronounced hallucinations in remote sensing visual question-answering (RS-VQA), primarily caused by visual grounding failures in large-scale scenes or misinterpretation of fine-grained small targets. To systematically analyze these issues, we introduce RSHBench, a protocol-based benchmark for fine-grained diagnosis of factual and logical hallucinations. To mitigate grounding-induced factual hallucinations, we further propose Relative Attention-Driven Actively Reasoning (RADAR), a training-free inference method that leverages intrinsic attention in MLLMs to guide progressive localization and fine-grained local reasoning at test time. Extensive experiments across diverse MLLMs demonstrate that RADAR consistently improves RS-VQA performance and reduces both factual and logical hallucinations. Code and data will be publicly available at: https://github.com/MiliLab/RADAR

Yi Liu, Jing Zhang, Di Wang +3

School of Computer Science, Wuhan University, China · Zhongguancun Academy, China · School of Computer Science, Chongqing University, China

Remote Sensing VQA VLM Hallucination Mitigation Multimodal Large Language Models Vision-Language Grounding Hallucination Detection in VLMs Remote Sensing Benchmarks

Mar 3, 2026

Real-Time Generation of Game Video Commentary with Multimodal LLMs: Pause-Aware Decoding Approaches

Real-time video commentary generation provides textual descriptions of ongoing events in videos. It supports accessibility and engagement in domains such as sports, esports, and livestreaming. Commentary generation involves two essential decisions: what to say and when to say it. While recent prompting-based approaches using multimodal large language models (MLLMs) have shown strong performance in content generation, they largely ignore the timing aspect. We investigate whether in-context prompting alone can support real-time commentary generation that is both semantically relevant and well-timed. We propose two prompting-based decoding strategies: 1) a fixed-interval approach, and 2) a novel dynamic interval-based decoding approach that adjusts the next prediction timing based on the estimated duration of the previous utterance. Both methods enable pause-aware generation without any fine-tuning. Experiments on Japanese and English datasets of racing and fighting games show that the dynamic interval-based decoding can generate commentary more closely aligned with human utterance timing and content using prompting alone. We release a multilingual benchmark dataset, trained models, and implementations to support future research on real-time video commentary generation.

Anum Afzal, Yuki Saito, Hiroya Takamura +5

School of CIT, Technical University of Munich · National Institute of Advanced Industrial Science and Technology (AIST) · The University of Tokyo +3

Language Model Decoding Multimodal Large Language Models Video-Language Models

Mar 3, 2026

On Discriminative vs. Generative classifiers: Rethinking MLLMs for Action Understanding

Multimodal Large Language Models (MLLMs) have advanced open-world action understanding and can be adapted as generative classifiers for closed-set settings by autoregressively generating action labels as text. However, this approach is inefficient, and shared subwords across action labels introduce semantic overlap, leading to ambiguity in generation. In contrast, discriminative classifiers learn task-specific representations with clear decision boundaries, enabling efficient one-step classification without autoregressive decoding. We first compare generative and discriminative classifiers with MLLMs for closed-set action understanding, revealing the superior accuracy and efficiency of the latter. To bridge the performance gap, we design strategies that elevate generative classifiers toward performance comparable with discriminative ones. Furthermore, we show that generative modeling can complement discriminative classifiers, leading to better performance while preserving efficiency. To this end, we propose Generation-Assisted Discriminative~(GAD) classifier for closed-set action understanding. GAD operates only during fine-tuning, preserving full compatibility with MLLM pretraining. Extensive experiments on temporal action understanding benchmarks demonstrate that GAD improves both accuracy and efficiency over generative methods, achieving state-of-the-art results on four tasks across five datasets, including an average 2.5% accuracy gain and 3x faster inference on our largest COIN benchmark.

Zhanzhong Pang, Dibyadip Chatterjee, Fadime Sener +1

National University of Singapore

Classification Multimodal Classification Multimodal Large Language Models Temporal Video Understanding

Mar 3, 2026

MUSE: A Run-Centric Platform for Multimodal Unified Safety Evaluation of Large Language Models

Safety evaluation of multimodal large language models requires tracking not only whether an attack succeeds, but also how the interaction unfolds across turns and input modalities. We present MUSE (Multimodal Unified Safety Evaluation), an open-source, browser-based, run-centric platform for multimodal safety evaluation. MUSE treats each attack run as the persistent unit of execution, inspection, and analysis, preserving its configuration, multi-turn trajectory, delivered modalities and media, target responses, and safety judgments. A five-level response taxonomy further distinguishes full Compliance from Partial Compliance and refusal behavior, yielding hard ASR, soft ASR, and gray-zone width (GZW). Across 11,700 evaluations on six multimodal LLMs, direct text-only requests yield only 3.1% macro hard ASR and 4.4% soft ASR, while iterative attack procedures are substantially more effective. Attack effectiveness also varies substantially with the attacker backbone. In contrast, Inter-Turn Modality Switching (ITMS), evaluated as a controlled delivery-modality probe, does not consistently increase attack success. These results demonstrate the value of run-centric, fine-grained evaluation for characterizing multimodal safety behavior beyond a single binary success metric.

Zhongxi Wang, Yueqian Lin, Jingyang Zhang +3

1Duke University · 2Virtue AI

LLM Safety Benchmarks LLM Safety Multi-Turn Jailbreak Attacks Language Model Safety Evaluation Multimodal Large Language Models Jailbreak Attacks+2

Mar 2, 2026

Nano-EmoX: Unifying Multimodal Emotional Intelligence from Perception to Empathy

The development of affective multimodal language models (MLMs) has long been constrained by a gap between low-level perception and high-level interaction, leading to fragmented affective capabilities and limited generalization. To bridge this gap, we propose a cognitively inspired three-level hierarchy that organizes affective tasks according to their cognitive depth-perception, understanding, and interaction-and provides a unified conceptual foundation for advancing affective modeling. Guided by this hierarchy, we introduce Nano-EmoX, a small-scale multitask MLM, and P2E (Perception-to-Empathy), a curriculum-based training framework. Nano-EmoX integrates a suite of omni-modal encoders, including an enhanced facial encoder and a fusion encoder, to capture key multimodal affective cues and improve cross-task transferability. The outputs are projected into a unified language space via heterogeneous adapters, empowering a lightweight language model to tackle diverse affective tasks. Concurrently, P2E progressively cultivates emotional intelligence by aligning rapid perception with chain-of-thought-driven empathy. To the best of our knowledge, Nano-EmoX is the first compact MLM (2.2B) to unify six core affective tasks across all three hierarchy levels, achieving state-of-the-art or highly competitive performance across multiple benchmarks, demonstrating excellent efficiency and generalization. The code is available at https://github.com/waHAHJIAHAO/Nano-EmoX.

Jiahao Huang, Fengyan Lin, Xuechao Yang +4

Fujian Normal University · RMIT University · Independent Researcher +1

Affective Computing Multimodal Large Language Models Multimodal Emotion Recognition

Mar 2, 2026

MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning

Recent progress in the reasoning capabilities of multimodal large language models (MLLMs) has empowered them to address more complex tasks such as scientific analysis and mathematical reasoning. Despite their promise, MLLMs' reasoning abilities across different scenarios in real life remain largely unexplored and lack standardized benchmarks for evaluation. To address this gap, we introduce MMR-Life, a comprehensive benchmark designed to evaluate the diverse multimodal multi-image reasoning capabilities of MLLMs across real-life scenarios. MMR-Life consists of 2,646 multiple-choice questions based on 19,108 images primarily sourced from real-world contexts, comprehensively covering seven reasoning types: abductive, analogical, causal, deductive, inductive, spatial, and temporal. Unlike existing reasoning benchmarks, MMR-Life does not rely on domain-specific expertise but instead requires models to integrate information across multiple images and apply diverse reasoning abilities. The evaluation of 37 advanced models highlights the substantial challenge posed by MMR-Life. Even top models like GPT-5 achieve only 58% accuracy and display considerable variance in performance across reasoning types. Moreover, we analyze the reasoning paradigms of existing MLLMs, exploring how factors such as thinking length, reasoning method, and reasoning type affect their performance. In summary, MMR-Life establishes a comprehensive foundation for evaluating, analyzing, and improving the next generation of multimodal reasoning systems.

Jiachun Li, Shaoping Huang, Zhuoran Jin +5

School of Artificial Intelligence, University of Chinese Academy of Sciences · The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences

Multi-Image Reasoning Multimodal Reasoning Visual Reasoning Multimodal Large Language Models Multimodal Model Evaluation

Mar 2, 2026

DeLo: Dual Decomposed Low-Rank Experts Collaboration for Continual Missing Modality Learning

Adapting Large Multimodal Models (LMMs) to real-world scenarios poses the dual challenges of learning from sequential data streams while handling frequent modality incompleteness, a task known as Continual Missing Modality Learning (CMML). However, existing works on CMML have predominantly relied on prompt tuning, a technique that struggles with this task due to cross-task interference between its learnable prompts in their shared embedding space. A naive application of Low-Rank Adaptation (LoRA) with modality-shared module will also suffer modality interference from competing gradients. To this end, we propose DeLo, the first framework to leverage a novel dual-decomposed low-rank expert architecture for CMML. Specifically, this architecture resolves modality interference through decomposed LoRA expert, dynamically composing LoRA update matrix with rank-one factors from disentangled modality-specific factor pools. Embedded within a task-partitioned framework that structurally prevents catastrophic forgetting, this expert system is supported by two key mechanisms: a Cross-Modal Guided Routing strategy to handle incomplete data and a Task-Key Memory for efficient, task-agnostic inference. Extensive experiments on established CMML benchmarks demonstrate that our method significantly outperforms state-of-the-art approaches. This highlights the value of a principled, architecturally-aware LoRA design for real-world multimodal challenges.

Xiwei Liu, Yulong Li, Feilong Tang +1

Mohamed bin Zayed University of Artificial Intelligence · Monash University

Missing-Modality Learning Multimodal Large Language Models Continual Learning for VLMs Low-Rank Adaptation

Mar 2, 2026

Children's Intelligence Tests Pose Challenges for MLLMs? KidGym: A 2D Grid-Based Reasoning Benchmark for MLLMs

Multimodal Large Language Models (MLLMs) combine the linguistic strengths of LLMs with the ability to process multimodal data, enbaling them to address a broader range of visual tasks. Because MLLMs aim at more general, human-like competence than language-only models, we take inspiration from the Wechsler Intelligence Scales - an established battery for evaluating children by decomposing intelligence into interpretable, testable abilities. We introduce KidGym, a comprehensive 2D grid-based benchmark for assessing five essential capabilities of MLLMs: Execution, Perception Reasoning, Learning, Memory and Planning. The benchmark comprises 12 unique tasks, each targeting at least one core capability, specifically designed to guage MLLMs' adaptability and developmental potential, mirroring the stages of children's cognitive growth. Additionally, our tasks encompass diverse scenarios and objects with randomly generated layouts, ensuring a more accurate and robust evluation of MLLM capabilities. KidGym is designed to be fully user-customizable and extensible, allowing researchers to create new evaluation scenarios and adjust difficuly levels to accommodate the rapidly growing MLLM community. Through the evaluation of state-of-the-art MLLMs using KidGym, we identified significant insights into model capabilities and revealed several limitations of current models. We release our benchmark at: https://bobo-ye.github.io/KidGym/.

Hengwei Ye, Yuanting Guan, Yuxuan Ge +7

ShanghaiTech University

Multimodal Model Evaluation Multimodal Large Language Models Spatial Reasoning Benchmarks Spatial Reasoning

Mar 2, 2026

Reconstructing Content with Collaborative Attention for Universal Multimodal Representation Learning

Multimodal embedding models, rooted in multimodal large language models (MLLMs), have yielded significant performance improvements across diverse tasks such as retrieval and classification. However, most existing approaches rely heavily on large-scale contrastive learning, with limited exploration of how the architectural and training paradigms of MLLMs affect embedding quality. While effective for generation, the causal attention and next-token prediction paradigm of MLLMs does not explicitly encourage the formation of globally compact representations, limiting their effectiveness as multimodal embedding backbones. To address this, we propose CoCoA, a Content reconstruction pre-training paradigm based on Collaborative Attention for multimodal embedding optimization. Specifically, we restructure the attention flow and introduce an EOS-based reconstruction task, encouraging the model to reconstruct input from the corresponding <EOS> embeddings. This drives the multimodal model to compress the semantic information of the input into the <EOS> token, laying the foundations for subsequent contrastive learning. Extensive experiments on MMEB-V1 demonstrate that CoCoA built upon Qwen2-VL and Qwen2.5-VL significantly improves embedding quality. Results validate that content reconstruction serves as an effective strategy to maximize the value of existing data, enabling multimodal embedding models generate compact and informative representations, raising their performance ceiling.

Jiahan Chen, Da Li, Hengran Zhang +6

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, University of Chinese Academy of Sciences, Beijing, China · Baidu Inc., Beijing, China

Multimodal Embedding Multimodal Learning Multimodal Pretraining Multimodal Large Language Models

Mar 1, 2026

Can Thinking Models Think to Detect Hateful Memes?

Hateful memes often require compositional multimodal reasoning: the image and text may appear benign in isolation, yet their interaction conveys harmful intent. Although thinking-based multimodal large language models (MLLMs) have recently advanced vision-language understanding, their capabilities remain underexplored for hateful meme analysis. We propose a reinforcement learning based post-training framework that improves reasoning in thinking-based MLLMs through task-specific rewards and a novel Group Relative Policy Optimization (GRPO) objective. Specifically, we (i) conduct a systematic empirical study of off-the-shelf MLLMs for hateful meme understanding, (ii) extend an existing hateful meme dataset by generating weakly or pseudo-supervised chain-of-thought rationales via distillation, and (iii) introduce a GRPO-based objective that jointly optimizes meme classification and explanation quality to encourage fine-grained, step-by-step reasoning. Experiments on the Hateful Memes benchmark show that our approach achieves state-of-the-art performance, improving accuracy and F1 by approximately 1 percent and explanation quality by approximately 3 percent. We will publicly release our code, dataset extensions, and evaluation resources to support reproducibility.

Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor +2

Qatar University Doha, Qatar · Qatar Computing Research Institute Doha, Qatar · APAVI.AI France +1

Harmful Meme Detection Multimodal Large Language Models Hate Speech Detection VLM Reasoning Content Moderation RL for Language Model Reasoning

Mar 1, 2026

FCN-LLM: Empower LLM for Brain Functional Connectivity Network Understanding via Graph-level Multi-task Instruction Tuning

Large Language Models have achieved remarkable success in language understanding and reasoning, and their multimodal extensions enable comprehension of images, video, and audio. Inspired by this, foundation models for brain functional connectivity networks derived from resting-state fMRI have shown promise in clinical tasks. However, existing methods do not align FCNs with the text modality, limiting the ability of LLMs to directly understand FCNs. To address this, we propose FCN-LLM, a framework that enables LLMs to understand FCNs through graph-level, multi-task instruction tuning. Our approach employs a multi-scale FCN encoder capturing brain-region, functional subnetwork, and whole-brain features, projecting them into the semantic space of LLM. We design multi-paradigm instruction tasks covering 19 subject-specific attributes across demographics, phenotypes, and psychiatric conditions. A multi-stage learning strategy first aligns FCN embeddings with the LLM and then jointly fine-tunes the entire model to capture high-level semantic information. Experiments on a large-scale, multi-site FCN database show that FCN-LLM achieves strong zero-shot generalization on unseen datasets, outperforming conventional supervised and foundation models. This work introduces a new paradigm for integrating brain functional networks with LLMs, offering a flexible and interpretable framework for neuroscience.

Xingcan Hu, Wei Wang, Li Xiao

University of Science and Technology of China

Brain Network Analysis Functional Connectivity Multimodal Large Language Models Instruction Tuning Multimodal Pretraining

Mar 1, 2026

From Intuition to Investigation: A Tool-Augmented Reasoning MLLM Framework for Generalizable Face Anti-Spoofing

Face recognition remains vulnerable to presentation attacks, calling for robust Face Anti-Spoofing (FAS) solutions. Recent MLLM-based FAS methods reformulate the binary classification task as the generation of brief textual descriptions to improve cross-domain generalization. However, their generalizability is still limited, as such descriptions mainly capture intuitive semantic cues (e.g., mask contours) while struggling to perceive fine-grained visual patterns. To address this limitation, we incorporate external visual tools into MLLMs to encourage deeper investigation of subtle spoof clues. Specifically, we propose the Tool-Augmented Reasoning FAS (TAR-FAS) framework, which reformulates the FAS task as a Chain-of-Thought with Visual Tools (CoT-VT) paradigm, allowing MLLMs to begin with intuitive observations and adaptively invoke external visual tools for fine-grained investigation. To this end, we design a tool-augmented data annotation pipeline and construct the ToolFAS-16K dataset, which contains multi-turn tool-use reasoning trajectories. Furthermore, we introduce a tool-aware FAS training pipeline, where Diverse-Tool Group Relative Policy Optimization (DT-GRPO) enables the model to autonomously learn efficient tool use. Extensive experiments under a challenging one-to-eleven cross-domain protocol demonstrate that TAR-FAS achieves SOTA performance while providing fine-grained visual investigation for trustworthy spoof detection.

Haoyuan Zhang, Keyao Wang, Guosheng Zhang +11

SAI, UCAS · MAIS, CASIA · Baidu Inc +2

Face Presentation Attack Detection Face Anti-Spoofing Multimodal Large Language Models

Mar 1, 2026

Seeing Beyond 8bits: Subjective and Objective Quality Assessment of HDR-UGC Videos

High Dynamic Range (HDR) user-generated (UGC) videos are rapidly proliferating across social platforms, yet most perceptual video quality assessment (VQA) systems remain tailored to Standard Dynamic Range (SDR). HDR has a higher bit depth, wide color gamut, and elevated luminance range, exposing distortions such as near-black crushing, highlight clipping, banding, and exposure flicker that amplify UGC artifacts and challenge SDR models. To catalyze progress, we curate Beyond8Bits, a large-scale subjective dataset of 44K videos from 6.5K sources with over 1.5M crowd ratings, spanning diverse scenes, capture conditions, and compression settings. We further introduce HDR-Q, the first Multimodal Large Language Model (MLLM) for HDR-UGC VQA. We propose (i) a novel HDR-aware vision encoder to produce HDR-sensitive embeddings, and (ii) HDR-Aware Policy Optimization (HAPO), an RL finetuning framework that anchors reasoning to HDR cues. HAPO augments GRPO via an HDR-SDR contrastive KL that encourages token reliance on HDR inputs and a Gaussian weighted regression reward for fine-grained MOS calibration. Across Beyond8Bits and public HDR-VQA benchmarks, HDR-Q delivers state-of-the-art performance.

Shreshth Saini, Bowen Chen, Neil Birkbeck +3

Laboratory for Image and Video Engineering (LIVE), UT Austin. · Google/YouTube

Video Quality Assessment HDR Imaging Multimodal Large Language Models

Feb 28, 2026

MARS: Harmonizing Multimodal Convergence via Adaptive Rank Search

Fine-tuning Multimodal Large Language Models (MLLMs) with parameter-efficient methods like Low-Rank Adaptation (LoRA) is crucial for task adaptation. However, imbalanced training dynamics across modalities often lead to suboptimal accuracy due to negative interference, a challenge typically addressed with inefficient heuristic methods such as manually tuning separate learning rates. To overcome this, we introduce MARS (Multimodal Adaptive Rank Search), an approach to discover optimal rank pairs that balance training dynamics while maximizing performance. Our key innovation, a proposed framework of dual scaling laws, enables this search: one law models module-specific convergence time to prune the search space to candidates with aligned dynamics, while the other predicts final task performance to select the optimal pair from the pruned set. By re-purposing the LoRA rank as a controller for modality-specific convergence speed, MARS outperforms baseline methods and provides a robust, automated strategy for optimizing MLLM fine-tuning.

Minkyoung Cho, Insu Jang, Shuowei Jin +5

University of Michigan · NVIDIA

Multimodal Large Language Models Multimodal Optimization Low-Rank Adaptation Scaling Laws

Feb 28, 2026

Mema: Memory-Augmented Adapter for Enhanced Vision-Language Understanding

Multimodal Large Language Models (MLLMs) have achieved remarkable performance by aligning pretrained visual representations with the linguistic knowledge embedded in Large Language Models (LLMs). However, existing approaches typically rely on final-layer visual features or learnable multi-layer fusion, which often fail to sufficiently exploit hierarchical visual cues without explicit cross-layer interaction design. In this work, we propose a Memory-Augmented Adapter (Mema) within the vision encoder. Specifically, Mema maintains a stateful memory that accumulates hierarchical visual representations across layers, with its evolution conditioned on both query embeddings and step-wise visual features. A portion of this memory is selectively injected into token representations via a feedback mechanism, thereby mitigating the attenuation of fine-grained visual cues from shallow layers. Designed as a lightweight and plug-and-play module, Mema integrates seamlessly into pretrained vision encoders without modifying the vanilla backbone architecture. Only a minimal set of additional parameters requires training, enabling adaptive visual feature refinement while reducing training overhead. Extensive experiments across multiple benchmarks demonstrate that Mema consistently improves performance, validating its effectiveness in complex multimodal reasoning tasks. The code have been released at https://github.com/Sisiliu312/Mema.

Ying Liu, Yudong Han, Kean Shi +1

Beijing Institute of Technology · Peking University · Yangtze Delta Region Academy of Beijing Institude of Technology, Jiaxing, China

Memory-Augmented VLMs Multimodal Large Language Models VLM Adaptation

Feb 28, 2026

UNICBench: UNIfied Counting Benchmark for MLLM

Counting is a core capability for multimodal large language models (MLLMs), yet there is no unified counting dataset to rigorously evaluate this ability across image, text, and audio. We present UNICBench, a unified multimodal, multi level counting benchmark and evaluation toolkit with accurate ground truth, deterministic numeric parsing, and stratified reporting. The corpus comprises 5,300 images (5,508 QA), 872 documents (5,888 QA), and 2,069 audio clips (2,905 QA), annotated with a three level capability taxonomy and difficulty tags. Under a standardized protocol with fixed splits/prompts/seeds and modality specific matching rules, we evaluate 45 state-of-the-art MLLMs across modalities. Results show strong performance on some basic counting tasks but significant gaps on reasoning and the hardest partitions, highlighting long-tail errors and substantial headroom for improving general counting. UNICBench offers a rigorous and comparable basis for measurement and a public toolkit to accelerate progress.

Chenggang Rong, Tao Han, Zhiyuan Zhao +5

Northwestern Polytechnical University · Hong Kong University of Science and Technology · Institute of Artificial Intelligence (TeleAI), China Telecom +2

Multimodal Large Language Models Multimodal Dataset Multimodal Model Evaluation

Feb 28, 2026

MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs

Multimodal Large Language Models (MLLMs) have achieved remarkable performance but remain vulnerable to jailbreak attacks that can induce harmful content and undermine their secure deployment. Previous studies have shown that introducing additional inference steps, which disrupt security attention, can make MLLMs more susceptible to being misled into generating malicious content. However, these methods rely on single-image masking or isolated visual cues, which only modestly extend reasoning paths and thus achieve limited effectiveness, particularly against strongly aligned commercial closed-source models. To address this problem, in this paper, we propose Multi-Image Dispersion and Semantic Reconstruction (MIDAS), a multimodal jailbreak framework that decomposes harmful semantics into risk-bearing subunits, disperses them across multiple visual clues, and leverages cross-image reasoning to gradually reconstruct the malicious intent, thereby bypassing existing safety mechanisms. The proposed MIDAS enforces longer and more structured multi-image chained reasoning, substantially increases the model's reliance on visual cues while delaying the exposure of malicious semantics and significantly reducing the model's security attention, thereby improving the performance of jailbreak against advanced MLLMs. Extensive experiments across different datasets and MLLMs demonstrate that the proposed MIDAS outperforms state-of-the-art jailbreak attacks for MLLMs and achieves an average attack success rate of 81.46% across 4 closed-source MLLMs. Our code is available at this link.

Yilian Liu, Xiaojun Jia, Guoshun Nan +6

Beijing University of Posts and Telecommunications, China · Nanyang Technological University, Singapore · Guilin University of Electronic Technology, China

Multimodal Jailbreak Attacks Adversarial Attacks on Unified Multimodal Models LLM Safety Multimodal Large Language Models

Feb 28, 2026

Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation

Using Multimodal Large Language Models (MLLMs) as judges to achieve precise and consistent evaluations has gradually become an emerging paradigm across various domains. Evaluating the capability and reliability of MLLM-as-a-judge systems is therefore essential for ensuring trustworthy assessment. Existing judge benchmarks categorize samples by task types but fail to capture the fundamental judgment capabilities required for reliable evaluation. In this work, we introduce M-JudgeBench, a ten-dimensional capability-oriented benchmark designed to comprehensively assess the judgment abilities of MLLMs. Our benchmark decomposes evaluation into pairwise Chain-of-Thought (CoT) comparison, length bias avoidance, and process error detection tasks, jointly covering ten fine-grained subtasks. This design enables diagnosis of model reliability across reasoning styles, response lengths, and cross-model variations. Systematic evaluation uncovers the systematic weaknesses in existing MLLM-as-a-judge systems. To address this issue, we further propose Judge-MCTS, a data construction framework generating pairwise reasoning trajectories with various correctness and length. Using Judge-MCTS, we construct an MCTS-augmented dataset and train M-Judger, a series of strong judge models. Extensive experiments demonstrate the superiority of M-Judger on existing judge benchmarks as well as M-JudgeBench. Overall, our work establishes a more principled foundation for evaluating MLLM-as-a-judge through M-JudgeBench and Judge-MCTS framework, paving the way for future research on judge model evaluation and capability-driven judge training.

Zeyu Chen, Huanjin Yao, Ziwang Zhao +1

LLM Evaluation LLM-as-a-Judge Synthetic Data Generation Multimodal Large Language Models Multimodal Model Evaluation

Feb 28, 2026

Pragma-VL: Towards a Pragmatic Arbitration of Safety and Helpfulness in MLLMs

Multimodal Large Language Models (MLLMs) pose critical safety challenges, as they are susceptible not only to adversarial attacks such as jailbreaking but also to inadvertently generating harmful content for benign users. While internal safety alignment via Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) is a primary mitigation strategy, current methods often face a safety-utility trade-off: they either refuse benign queries out of excessive caution or overlook latent risks in cross-modal interactions. To resolve this, we introduce Pragma-VL, an end-to-end alignment algorithm that enables MLLMs to pragmatically arbitrate between safety and helpfulness. First, we enhance visual risk perception with a novel cold-start SFT stage. This is achieved by applying risk-aware clustering to the visual encoder and using an interleaved dataset of risk descriptions and high-quality data. Second, we introduce a theoretically-guaranteed reward model that leverages synergistic learning. We train it with a novel data augmentation method that assigns dynamic weights based on the queries, enabling contextual arbitration between safety and helpfulness. Extensive experiments show that Pragma-VL effectively balances safety and helpfulness, outperforming baselines by 5% to 20% on most multimodal safety benchmarks while preserving its general capabilities in areas such as mathematics and knowledge reasoning.

Ming Wen, Kun Yang, Xin Chen +4

Fudan University · Shanghai Innovation Institute · Ant Group +3

Multimodal Large Language Models LLM Safety Alignment Reward Modeling

Feb 28, 2026

MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence

Humans are born with vision-based 4D spatial-temporal intelligence, which enables us to perceive and reason about the evolution of 3D space over time from purely visual inputs. Despite its importance, this capability remains a significant bottleneck for current multimodal large language models (MLLMs). To tackle this challenge, we introduce MLLM-4D, a comprehensive framework designed to bridge the gaps in training data curation and model post-training for spatiotemporal understanding and reasoning. On the data front, we develop a cost-efficient data curation pipeline that repurposes existing stereo video datasets into high-quality 4D spatiotemporal instructional data. This results in the MLLM4D-2M and MLLM4D-R1-30k datasets for Supervised Fine-Tuning (SFT) and Reinforcement Fine-Tuning (RFT), alongside MLLM4D-Bench for comprehensive evaluation. Regarding model training, our post-training strategy establishes a foundational 4D understanding via SFT and further catalyzes 4D reasoning capabilities by employing Group Relative Policy Optimization (GRPO) with specialized Spatiotemporal Chain of Thought (ST-CoT) prompting and Spatiotemporal reward functions (ST-reward) without involving the modification of architecture. Extensive experiments demonstrate that MLLM-4D achieves state-of-the-art spatial-temporal understanding and reasoning capabilities from purely 2D RGB inputs. Project page: https://github.com/GVCLab/MLLM-4D.

Xingyilang Yin, Chengzhengxu Li, Jiahao Chang +2

University of Macau · GVC Lab, Great Bay University · Xi’an Jiaotong University +1

Spatiotemporal Reasoning Multimodal Large Language Models VLM Reasoning 4D Scene Understanding