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.

Feb 23, 2026

Test-Time Computing for Referring Multimodal Large Language Models

We propose ControlMLLM++, a novel test-time adaptation framework that injects learnable visual prompts into frozen multimodal large language models (MLLMs) to enable fine-grained region-based visual reasoning without any model retraining or fine-tuning. Leveraging the insight that cross-modal attention maps intrinsically encode semantic correspondences between textual tokens and visual regions, ControlMLLM++ optimizes a latent visual token modifier during inference via a task-specific energy function to steer model attention towards user-specified areas. To enhance optimization stability and mitigate language prompt biases, ControlMLLM++ incorporates an improved optimization strategy (Optim++) and a prompt debiasing mechanism (PromptDebias). Supporting diverse visual prompt types including bounding boxes, masks, scribbles, and points, our method demonstrates strong out-of-domain generalization and interpretability. The code is available at https://github.com/mrwu-mac/ControlMLLM.

Mingrui Wu, Hao Chen, Jiayi Ji +5

Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, 361005, P.R. China. · Zhongguancun Academy, Beijing, China.100094. · Tsinghua University. +1

Test-Time Adaptation of VLMs Multimodal Large Language Models Visual Reasoning Visual Prompt Learning

Feb 22, 2026

PositionOCR: Augmenting Positional Awareness in Multi-Modal Models via Hybrid Specialist Integration

In recent years, Multi-modal Large Language Models (MLLMs) have achieved strong performance in OCR-centric Visual Question Answering (VQA) tasks, illustrating their capability to process heterogeneous data and exhibit adaptability across varied contexts. However, these MLLMs rely on a Large Language Model (LLM) as the decoder, which is primarily designed for linguistic processing, and thus inherently lacks the positional reasoning required for precise visual tasks, such as text spotting and text grounding. Additionally, the extensive parameters of MLLMs necessitate substantial computational resources and large-scale data for effective training. Conversely, text spotting specialists achieve state-of-the-art coordinate predictions but lack semantic reasoning capabilities. This dichotomy motivates our key research question: Can we synergize the efficiency of specialists with the contextual power of LLMs to create a positionally-accurate MLLM? To overcome these challenges, we introduce PositionOCR, a parameter-efficient hybrid architecture that seamlessly integrates a text spotting model's positional strengths with an LLM's contextual reasoning. Comprising 131M trainable parameters, this framework demonstrates outstanding multi-modal processing capabilities, particularly excelling in tasks such as text grounding and text spotting, consistently surpassing traditional MLLMs.

Chen Duan, Zhentao Guo, Pei Fu +3

Multimodal Large Language Models Optical Character Recognition Visual Question Answering

Feb 22, 2026

CREM: Compression-Driven Representation Enhancement for Multimodal Retrieval and Comprehension

Multimodal Large Language Models (MLLMs) have shown remarkable success in comprehension tasks such as visual description and visual question answering. However, their direct application to embedding-based tasks like retrieval remains challenging due to the discrepancy between output formats and optimization objectives. Previous approaches often employ contrastive fine-tuning to adapt MLLMs for retrieval, but at the cost of losing their generative capabilities. We argue that both generative and embedding tasks fundamentally rely on shared cognitive mechanisms, specifically cross-modal representation alignment and contextual comprehension. To this end, we propose CREM (Compression-driven Representation Enhanced Model), with a unified framework that enhances multimodal representations for retrieval while preserving generative ability. Specifically, we introduce a compression-based prompt design with learnable chorus tokens to aggregate multimodal semantics and a compression-driven training strategy that integrates contrastive and generative objectives through compression-aware attention. Extensive experiments demonstrate that CREM achieves state-of-the-art retrieval performance on MMEB while maintaining strong generative performance on multiple comprehension benchmarks. Our findings highlight that generative supervision can further improve the representational quality of MLLMs under the proposed compression-driven paradigm.

Lihao Liu, Yan Wang, Biao Yang +10

Tsinghua University · Kuaishou Technology

Multimodal Large Language Models Cross-Modal Retrieval Multimodal Embedding Cross-Modal Representation Learning Multimodal Understanding Multimodal Token Compression

Feb 21, 2026

TPRU: Advancing Temporal and Procedural Understanding in Large Multimodal Models

Multimodal Large Language Models (MLLMs), particularly smaller, deployable variants, exhibit a critical deficiency in understanding temporal and procedural visual data, a bottleneck hindering their application in real-world embodied AI. This gap is largely caused by a systemic failure in training paradigms, which lack large-scale, procedurally coherent data. To address this problem, we introduce TPRU, a large-scale dataset sourced from diverse embodied scenarios such as robotic manipulation and GUI navigation. TPRU is systematically designed to cultivate temporal reasoning through three complementary tasks: Temporal Reordering, Next-Frame Prediction, and Previous-Frame Review. A key feature is the inclusion of challenging negative samples, compelling models to transition from passive observation to active, cross-modal validation. We leverage TPRU with a reinforcement learning (RL) fine-tuning methodology, specifically targeting the enhancement of resource-efficient models. Experiments show our approach yields dramatic gains: on our manually curated TPRU-Test, the accuracy of TPRU-7B soars from 50.33% to 75.70%, a state-of-the-art result that significantly outperforms vastly larger baselines, including GPT-4o. Crucially, these capabilities generalize effectively, demonstrating substantial improvements on established benchmarks. The codebase is available at https://github.com/Stephen-gzk/TPRU/ .

Zhenkun Gao, Xuhong Wang, Xin Tan +1

East China Normal University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · Shanghai Innovation Institute, Shanghai, China

Temporal Reasoning in Language Models Multimodal Large Language Models

Feb 21, 2026

Beyond Description: A Multimodal Agent Framework for Insightful Chart Summarization

Chart summarization is crucial for enhancing data accessibility and the efficient consumption of information. However, existing methods, including those with Multimodal Large Language Models (MLLMs), primarily focus on low-level data descriptions and often fail to capture the deeper insights which are the fundamental purpose of data visualization. To address this challenge, we propose Chart Insight Agent Flow, a plan-and-execute multi-agent framework effectively leveraging the perceptual and reasoning capabilities of MLLMs to uncover profound insights directly from chart images. Furthermore, to overcome the lack of suitable benchmarks, we introduce ChartSummInsights, a new dataset featuring a diverse collection of real-world charts paired with high-quality, insightful summaries authored by human data analysis experts. Experimental results demonstrate that our method significantly improves the performance of MLLMs on the chart summarization task, producing summaries with deep and diverse insights.

Yuhang Bai, Yujuan Ding, Shanru Lin +1

The Hong Kong Polytechnic University · City University of Hong Kong

Chart Understanding Data Analysis Agents Multi-Agent LLMs Multimodal Large Language Models

Feb 20, 2026

Rodent-Bench

We present Rodent-Bench, a novel benchmark designed to evaluate the ability of Multimodal Large Language Models (MLLMs) to annotate rodent behaviour footage. We evaluate state-of-the-art MLLMs, including Gemini-2.5-Pro, Gemini-2.5-Flash and Qwen-VL-Max, using this benchmark and find that none of these models perform strongly enough to be used as an assistant for this task. Our benchmark encompasses diverse datasets spanning multiple behavioral paradigms including social interactions, grooming, scratching, and freezing behaviors, with videos ranging from 10 minutes to 35 minutes in length. We provide two benchmark versions to accommodate varying model capabilities and establish standardized evaluation metrics including second-wise accuracy, macro F1, mean average precision, mutual information, and Matthew's correlation coefficient. While some models show modest performance on certain datasets (notably grooming detection), overall results reveal significant challenges in temporal segmentation, handling extended video sequences, and distinguishing subtle behavioral states. Our analysis identifies key limitations in current MLLMs for scientific video annotation and provides insights for future model development. Rodent-Bench serves as a foundation for tracking progress toward reliable automated behavioral annotation in neuroscience research.

Thomas Heap, Laurence Aitchison, Emma Cahill +1

University of Bristol, Bristol, UK

Animal Behavior Analysis Video-Language Model Evaluation Multimodal Large Language Models Multimodal Model Evaluation

Feb 20, 2026

Continual-NExT: A Unified Comprehension And Generation Continual Learning Framework

Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibiting strong instantaneous learning and generalization capabilities, Dual-to-Dual MLLMs still remain deficient in lifelong evolution, significantly affecting continual adaptation to dynamic real-world scenarios. One of the challenges is that learning new tasks inevitably destroys the learned knowledge. Beyond traditional catastrophic forgetting, Dual-to-Dual MLLMs face other challenges, including hallucination, instruction unfollowing, and failures in cross-modal knowledge transfer. However, no standardized continual learning framework for Dual-to-Dual MLLMs has been established yet, leaving these challenges unexplored. Thus, in this paper, we establish Continual-NExT, a continual learning framework for Dual-to-Dual MLLMs with deliberately-architected evaluation metrics. To improve the continual learning capability of Dual-to-Dual MLLMs, we propose an efficient MAGE (Mixture and Aggregation of General LoRA and Expert LoRA) method to further facilitate knowledge transfer across modalities and mitigate forgetting. Extensive experiments demonstrate that MAGE outperforms other continual learning methods and achieves state-of-the-art performance.

Jingyang Qiao, Zhizhong Zhang, Xin Tan +3

East China Normal University · Shanghai Innovation Institute · Shanghai Artificial Intelligence Laboratory +1

Cross-Modal Representation Transfer Multimodal Large Language Models Unified Multimodal Models Transfer Learning Parameter-Efficient Fine-Tuning

Feb 20, 2026

Re-purposing Multimodal Large Language Models for Audio-Text Retrieval

Audio-text retrieval is crucial for bridging acoustic signals and natural language. While contrastive dual-encoder architectures like CLAP have shown promise, they are fundamentally limited by the capacity of small-scale encoders. Specifically, the text encoders struggle to understand complex queries that require reasoning or world knowledge. In this paper, we propose AuroLA, a novel contrastive language-audio pre-trained model that re-purposes Multimodal Large Language Models (MLLMs) as a unified backbone for audio-text retrieval. Specifically, we make the following contributions: (i) we construct a scalable data pipeline that curates diverse audio from multiple sources and generates multi-granular captions, ranging from long descriptions to structured tags, via automated annotation; (ii) we adapt an MLLM for retrieval by prompting it to summarise the audio/text input and using the hidden state of a special token as audio/text embeddings. (iii) extensive experiments demonstrate that AuroLA consistently outperforms state-of-the-art dual-encoder models, including the recent PE-AV. This validates the effectiveness of MLLM as a unified backbone for audio-text retrieval.

Jilan Xu, Carl Thomé, Danijela Horak +2

Visual Geometry Group, University of Oxford · Epidemic Sound · School of Artificial Intelligence, Shanghai Jiao Tong University

Multimodal Large Language Models Audio Understanding Audio-Language Models Audio-Text Retrieval Multimodal Contrastive Learning

Feb 19, 2026

Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models

With recent advancements in video backbone architectures, combined with the remarkable achievements of large language models (LLMs), the analysis of long-form videos spanning tens of minutes has become both feasible and increasingly prevalent. However, the inherently redundant nature of video sequences poses significant challenges for contemporary state-of-the-art models. These challenges stem from two primary aspects: 1) efficiently incorporating a larger number of frames within memory constraints, and 2) extracting discriminative information from the vast volume of input data. In this paper, we introduce a novel end-to-end schema for long-form video understanding, which includes an information-density-based adaptive video sampler (AVS) and an autoencoder-based spatiotemporal video compressor (SVC) integrated with a multimodal large language model (MLLM). Our proposed system offers two major advantages: it adaptively and effectively captures essential information from video sequences of varying durations, and it achieves high compression rates while preserving crucial discriminative information. The proposed framework demonstrates promising performance across various benchmarks, excelling in both long-form video understanding tasks and standard video understanding benchmarks. These results underscore the versatility and efficacy of our approach, particularly in managing the complexities of prolonged video sequences.

Yuxiao Chen, Jue Wang, Zhikang Zhang +8

Amazon AGI

Adaptive Video Frame Sampling Long-Video Understanding Video Token Compression Adaptive Sampling Multimodal Large Language Models

Feb 19, 2026

EAGLE: Expert-Augmented Attention Guidance for Tuning-Free Industrial Anomaly Detection in Multimodal Large Language Models

Multimodal large language models (MLLMs) can enrich industrial anomaly detection with semantic descriptions and anomaly reasoning, but they still lag specialist anomaly detectors in binary detection accuracy. Existing approaches address this gap by fine-tuning MLLMs or training bridging modules to align expert outputs with MLLM inputs, limiting flexibility across backbones. We propose EAGLE, a tuning-free framework that integrates expert anomaly detectors with frozen MLLMs. EAGLE consists of Threshold-Guided Prompt Selection (TGPS), which estimates a decision threshold from expert model statistics and selects textual and visual prompts, and Confidence-Aware Attention Sharpening (CAAS), which shifts MLLM attention toward visual evidence when expert confidence is low. Beyond improving accuracy, we analyze MLLM attention and find that correct anomaly predictions are associated with stronger focus on ground-truth defect regions; EAGLE consistently strengthens this alignment. On MVTec-AD and VisA, EAGLE improves five MLLM backbones without parameter updates, reaching up to 94.4% and 88.1% in anomaly discrimination accuracy, respectively, and achieving performance competitive with fine-tuning-based methods while largely preserving MLLM semantic reasoning ability.

Xiaomeng Peng, Xilang Huang, Seon Han Choi

Ewha Womans University

Anomaly Detection Industrial Anomaly Detection Multimodal Anomaly Detection Multimodal Large Language Models

Feb 19, 2026

EntropyPrune: Matrix Entropy Guided Visual Token Pruning for Multimodal Large Language Models

Multimodal large language models (MLLMs) incur substantial inference cost due to the processing of hundreds of visual tokens per image. Although token pruning has proven effective for accelerating inference, determining when and where to prune remains largely heuristic. Existing approaches typically rely on static, empirically selected layers, which limit interpretability and transferability across models. In this work, we introduce a matrix-entropy perspective and identify an "Entropy Collapse Layer" (ECL), where the information content of visual representations exhibits a sharp and consistent drop, which provides a principled criterion for selecting the pruning stage. Building on this observation, we propose EntropyPrune, a novel matrix-entropy-guided token pruning framework that quantifies the information value of individual visual tokens and prunes redundant ones without relying on attention maps. Moreover, to enable efficient computation, we exploit the spectral equivalence of dual Gram matrices, reducing the complexity of entropy computation and yielding up to a 64x theoretical speedup. Extensive experiments on diverse multimodal benchmarks demonstrate that EntropyPrune consistently outperforms state-of-the-art pruning methods in both accuracy and efficiency. On LLaVA-1.5-7B, our method achieves a 68.2% reduction in FLOPs while preserving 96.0% of the original performance. Furthermore, EntropyPrune generalizes effectively to high-resolution and video-based models, highlighting the strong robustness and scalability in practical MLLM acceleration. The code will be publicly available at https://github.com/YahongWang1/EntropyPrune.

Yahong Wang, Juncheng Wu, Zhangkai Ni +6

Tongji University · University of California, Santa Cruz · East China Normal University +1

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

Feb 18, 2026

ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding

While multimodal large language models (MLLMs) have shown remarkable success across a wide range of tasks, long-form video understanding remains a significant challenge. In this study, we focus on video understanding by MLLMs. This task is challenging because processing a full stream of RGB frames is computationally intractable and highly redundant, as self-attention have quadratic complexity with sequence length. In this paper, we propose ReMoRa, a video MLLM that processes videos by operating directly on their compressed representations. A sparse set of RGB keyframes is retained for appearance, while temporal dynamics are encoded as a motion representation, removing the need for sequential RGB frames. These motion representations act as a compact proxy for optical flow, capturing temporal dynamics without full frame decoding. To refine the noise and low fidelity of block-based motions, we introduce a module to denoise and generate a fine-grained motion representation. Furthermore, our model compresses these features in a way that scales linearly with sequence length. We demonstrate the effectiveness of ReMoRa through extensive experiments across a comprehensive suite of long-video understanding benchmarks. ReMoRa outperformed baseline methods on multiple challenging benchmarks, including LongVideoBench, NExT-QA, and MLVU.

Daichi Yashima, Shuhei Kurita, Yusuke Oda +1

Keio University · NII LLMC · NII

Long-Video Understanding Multimodal Large Language Models Video Representation Learning Motion Representation Learning

Feb 17, 2026

ViTaB-A: Evaluating Multimodal Large Language Models on Visual Table Attribution

Multimodal Large Language Models (mLLMs) are often used to answer questions in structured data such as tables in Markdown, JSON, and images. While these models can often give correct answers, users also need to know where those answers come from. In this work, we study structured data attribution/citation, which is the ability of the models to point to the specific rows and columns that support an answer. We evaluate several mLLMs across different table formats and prompting strategies. Our results show a clear gap between question answering and evidence attribution. Although question answering accuracy remains moderate, attribution accuracy is much lower, near random for JSON inputs, across all models. We also find that models are more reliable at citing rows than columns, and struggle more with textual formats than images. Finally, we observe notable differences across model families. Overall, our findings show that current mLLMs are unreliable at providing fine-grained, trustworthy attribution for structured data, which limits their usage in applications requiring transparency and traceability.

Yahia Alqurnawi, Preetom Biswas, Anmol Rao +3

School of Computing and Augmented Intelligence Arizona State University Tempe, AZ 85281, USA

Multimodal Large Language Models LLM Grounding Multimodal Model Evaluation

Feb 17, 2026

Beyond Binary Classification: Detecting Fine-Grained Sexism in Social Media Videos

Online sexism appears in various forms, which makes its detection challenging. Although automated tools can enhance the identification of sexist content, they are often restricted to binary classification. Consequently, more subtle manifestations of sexism may remain undetected due to the lack of fine-grained, context-sensitive labels. To address this issue, we make the following contributions: (1) we present FineMuSe, a new multimodal sexism detection dataset in Spanish that includes both binary and fine-grained annotations; (2) we introduce a comprehensive hierarchical taxonomy that encompasses forms of sexism, non-sexism, and rhetorical devices of irony and humor; and (3) we evaluate a wide range of LLMs for both binary and fine-grained sexism detection. Our findings indicate that multimodal LLMs perform competitively with human annotators in identifying nuanced forms of sexism; however, they struggle to capture co-occurring sexist types when these are conveyed through visual cues.

Laura De Grazia, Danae Sánchez Villegas, Desmond Elliott +2

CLiC – Language and Computing Center, University of Barcelona · Department of Computer Science, University of Copenhagen

Multimodal Large Language Models

Feb 17, 2026

KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR

Kazakh is a Turkic language using the Arabic, Cyrillic, and Latin scripts, making it unique in terms of optical character recognition (OCR). Work on OCR for low-resource Kazakh scripts is very scarce, and no OCR benchmarks or images exist for the Arabic and Latin scripts. We construct a synthetic OCR dataset of 7,219 images for all three scripts with font, color, and noise variations to imitate real OCR tasks. We evaluated three multimodal large language models (MLLMs) on a subset of the benchmark for OCR and language identification: Gemma-3-12B-it, Qwen2.5-VL-7B-Instruct, and Llama-3.2-11B-Vision-Instruct. All models are unsuccessful with Latin and Arabic script OCR, and fail to recognize the Arabic script as Kazakh text, misclassifying it as Arabic, Farsi, and Kurdish. We further compare MLLMs with a classical OCR baseline and find that while traditional OCR has lower character error rates, MLLMs fail to match this performance. These findings show significant gaps in current MLLM capabilities to process low-resource Abjad-based scripts and demonstrate the need for inclusive models and benchmarks supporting low-resource scripts and languages.

Henry Gagnier, Sophie Gagnier, Ashwin Kirubakaran

Pittsford Sutherland High School · Edison Academy Magnet School

Optical Character Recognition Low-Resource Language Processing Multimodal Model Evaluation Multimodal Large Language Models Language Identification

Feb 17, 2026

HIMM: Human-Inspired Long-Term Memory Modeling for Embodied Exploration and Question Answering

Deploying Multimodal Large Language Models as the brain of embodied agents remains challenging, particularly under long-horizon observations and limited context budgets. Existing memory assisted methods often rely on textual summaries, which discard rich visual and spatial details and remain brittle in non-stationary environments. In this work, we propose a non-parametric memory framework that explicitly disentangles episodic and semantic memory for embodied exploration and question answering. Our retrieval-first, reasoning-assisted paradigm recalls episodic experiences via semantic similarity and verifies them through visual reasoning, enabling robust reuse of past observations without rigid geometric alignment. In parallel, we introduce a program-style rule extraction mechanism that converts experiences into structured, reusable semantic memory, facilitating cross-environment generalization. Extensive experiments demonstrate state-of-the-art performance on embodied question answering and exploration benchmarks, yielding a 7.3% gain in LLM-Match and an 11.4% gain in LLM MatchXSPL on A-EQA, as well as +7.7% success rate and +6.8% SPL on GOAT-Bench. Analyses reveal that our episodic memory primarily improves exploration efficiency, while semantic memory strengthens complex reasoning of embodied agents.

Ji Li, Bo Wang, Jing Xia +2

The University of Hong Kong, Hong Kong SAR. · Beijing Institute of Technology, Beijing, China.

Long-Term Memory for Embodied Agents Memory-Augmented Agents Embodied AI Embodied QA Multimodal Large Language Models

Feb 17, 2026

Emergent Morphing Attack Detection in Open Multi-modal Large Language Models

Face morphing attacks threaten biometric verification, yet most morphing attack detection (MAD) systems require task-specific training and generalize poorly to unseen attack types. Meanwhile, open-source multimodal large language models (MLLMs) have demonstrated strong visual-linguistic reasoning, but their potential in biometric forensics remains underexplored. In this paper, we present the first systematic zero-shot evaluation of open-source MLLMs for single-image MAD, using publicly available weights and a standardized, reproducible protocol. Across diverse morphing techniques, many MLLMs show non-trivial discriminative ability without any fine-tuning or domain adaptation, and LLaVA1.6-Mistral-7B achieves state-of-the-art performance, surpassing highly competitive task-specific MAD baselines by at least 23% in terms of equal error rate (EER). The results indicate that multimodal pretraining can implicitly encode fine-grained facial inconsistencies indicative of morphing artifacts, enabling zero-shot forensic sensitivity. Our findings position open-source MLLMs as reproducible, interpretable, and competitive foundations for biometric security and forensic image analysis. This emergent capability also highlights new opportunities to develop state-of-the-art MAD systems through targeted fine-tuning or lightweight adaptation, further improving accuracy and efficiency while preserving interpretability. To support future research, all code and evaluation protocols will be released upon publication.

Marija Ivanovska, Vitomir Štruc

Faculty of Electrical Engineering, University of Ljubljana, Tržaška cesta 25, Ljubljana, 1000, Slovenia

Image Forgery Detection Face Presentation Attack Detection Multimodal Large Language Models Zero-Shot Learning Multimodal Model Evaluation

Feb 16, 2026

RF-GPT: Teaching AI to See the Wireless World

Large language models (LLMs) and multimodal models have become powerful general-purpose reasoning systems. However, radio-frequency (RF) signals, which underpin wireless systems, are still not natively supported by these models. Existing LLM-based approaches for telecom focus mainly on text and structured data, while conventional RF deep-learning models are built separately for specific signal-processing tasks, highlighting a clear gap between RF perception and high-level reasoning. To bridge this gap, we introduce RF-GPT, a radio-frequency language model (RFLM) that utilizes the visual encoders of multimodal LLMs to process and understand RF spectrograms. In this framework, complex in-phase/quadrature (IQ) waveforms are mapped to time-frequency spectrograms and then passed to pretrained visual encoders. The resulting representations are injected as RF tokens into a decoder-only LLM, which generates RF-grounded answers, explanations, and structured outputs. To train RF-GPT, we perform supervised instruction fine-tuning of a pretrained multimodal LLM using a fully synthetic RF corpus. Standards-compliant waveform generators produce wideband scenes for six wireless technologies, from which we derive time-frequency spectrograms, exact configuration metadata, and dense captions. A text-only LLM then converts these captions into RF-grounded instruction-answer pairs, yielding roughly 120,000 RF scenes and 0.625 million instruction examples without any manual labeling. Across benchmarks for wideband modulation classification, overlap analysis, wireless-technology recognition, WLAN user counting, and 5G NR information extraction, RF-GPT achieves strong multi-task performance, whereas general-purpose VLMs with no RF grounding largely fail.

Hang Zou, Yu Tian, Bohao Wang +4

Research Institute for Digital Future, Khalifa University, 127788 Abu Dhabi, UAE · College of Information Science and Electronic Engineering, Zhejiang University, 310027, Hangzhou, China · Université de Lorraine, CNRS, CRAN, F-54000 Nancy, France

Wireless Communications Language Modeling Multimodal Large Language Models

Feb 16, 2026

MATEO: A Multimodal Benchmark for Temporal Reasoning and Planning in LVLMs

AI agents need to plan to achieve complex goals that involve orchestrating perception, sub-goal decomposition, and execution. These plans consist of ordered steps structured according to a Temporal Execution Order (TEO, a directed acyclic graph that ensures each step executes only after its preconditions are satisfied. Existing research on foundational models' understanding of temporal execution is limited to automatically derived annotations, approximations of the TEO as a linear chain, or text-only inputs. To address this gap, we introduce MATEO (MultimodAl Temporal Execution Order), a benchmark designed to assess and improve the temporal reasoning abilities of Large Vision Language Models (LVLMs) required for real-world planning. We acquire a high-quality professional multimodal recipe corpus, authored through a standardized editorial process that decomposes instructions into discrete steps, each paired with corresponding images. We collect TEO annotations as graphs by designing and using a scalable crowdsourcing pipeline. Using MATEO, we evaluate six state-of-the-art LVLMs across model scales, varying language context, multimodal input structure, and fine-tuning strategies.

Gabriel Roccabruna, Olha Khomyn, Giuseppe Riccardi

Signals and Interactive Systems Lab, University of Trento, Italy

Temporal Reasoning in VLMs VLM Reasoning Multimodal Large Language Models Multimodal Reasoning

Feb 16, 2026

Diagnosing Knowledge Conflict in Multimodal Long-Chain Reasoning

Multimodal large language models (MLLMs) in long chain-of-thought reasoning often fail when different knowledge sources provide conflicting signals. We formalize these failures under a unified notion of knowledge conflict, distinguishing input-level objective conflict from process-level effective conflict. Through probing internal representations, we reveal that: (I) Linear Separability: different conflict types are explicitly encoded as linearly separable features rather than entangled; (II) Depth Localization: conflict signals concentrate in mid-to-late layers, indicating a distinct processing stage for conflict encoding; (III) Hierarchical Consistency: aggregating noisy token-level signals along trajectories robustly recovers input-level conflict types; and (IV) Directional Asymmetry: reinforcing the model's implicit source preference under conflict is far easier than enforcing the opposite source. Our findings provide a mechanism-level view of multimodal reasoning under knowledge conflict and enable principled diagnosis and control of long-CoT failures.

Jing Tang, Kun Wang, Haolang Lu +7

Huazhong University of Science and Technology · Nanyang Technological University · Beijing University of Posts and Telecommunications +2

Knowledge Conflicts in Language Models Multimodal Large Language Models Multimodal CoT Reasoning Multimodal Model Interpretability

Feb 12, 2026

Beyond Pixels: A Vector-to-Graph Framework for Reliable Schematic Auditing

Multimodal Large Language Models (MLLMs) have shown remarkable progress in visual understanding, yet they suffer from a critical limitation: structural blindness. Even state-of-the-art models fail to capture topology and symbolic logic in engineering schematics, as their pixel-driven paradigm discards the explicit vector-defined relations needed for reasoning. To overcome this, we propose a Vector-to-Graph (V2G) pipeline that converts CAD diagrams into property graphs where nodes represent components and edges encode connectivity, making structural dependencies explicit and machine-auditable. On a diagnostic benchmark of electrical compliance checks, V2G yields large accuracy gains across all error categories, while leading MLLMs remain near chance level. These results highlight the systemic inadequacy of pixel-based methods and demonstrate that structure-aware representations provide a reliable path toward practical deployment of multimodal AI in engineering domains. To facilitate further research, we release our benchmark and implementation at https://github.com/gm-embodied/V2G-Audit.

Chengwei Ma, Zhen Tian, Zhou Zhou +5

Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China · Guangdong Power Grid Co., Ltd., Yangjiang Power Supply Bureau, Yangjiang, China · Shanghai University, Shanghai, China +1

Multimodal Large Language Models Multimodal Model Evaluation

Feb 6, 2026

Ex-Omni: Enabling 3D Facial Animation Generation for Omni-modal Large Language Models

Omni-modal large language models (OLLMs) aim to unify multimodal understanding and generation, yet extending them to jointly produce speech and 3D facial animation remains largely underexplored. A key challenge is the mismatch between the discrete semantic reasoning of LLMs and the dense temporal dynamics required for 3D facial motion. We propose Expressive Omni (Ex-Omni), a framework that augments OLLMs with speech-accompanied 3D facial animation. Ex-Omni decouples semantic reasoning from temporal generation through a speech-unit generator with blendshape co-supervision and a non-autoregressive blendshape decoder, where speech units provide temporal scaffolding and hidden speech representations carry facially relevant cues. We further introduce a token-as-query gated fusion (TQGF) interface for controlled semantic injection, as well as InstructS2SF-1200K, a 1.2M-sample weakly supervised dataset for speech-accompanied facial animation. Extensive experiments show that Ex-Omni retains competitive speech QA capability while natively generating coordinated text, speech, and 3D facial animation, and approaches the Audio2Face-3D teacher cascade in synchronization and human preference.

Haoyu Zhang, Zhipeng Li, Yiwen Guo +1

The Chinese University of Hong Kong, Shenzhen · LIGHTSPEED · Independent Researcher

Multimodal Large Language Models Audio-Driven Facial Animation Multimodal Generation Facial Expression Synthesis

Feb 5, 2026

Multimodal Latent Reasoning via Hierarchical Visual Cues Injection

The advancement of multimodal large language models (MLLMs) has enabled impressive perception capabilities. However, their reasoning process often remains a "fast thinking" paradigm, reliant on end-to-end generation or explicit, language-centric chains of thought (CoT), which can be inefficient, verbose, and prone to hallucination. This work posits that robust reasoning should evolve within a latent space, integrating multimodal signals seamlessly. We propose multimodal latent reasoning via HIerarchical Visual cuEs injection (HIVE), a novel framework that instills deliberate, "slow thinking" without depending on superficial textual rationales. Our method recursively extends transformer blocks, creating an internal loop for iterative reasoning refinement. Crucially, it injectively grounds this process with hierarchical visual cues from global scene context to fine-grained regional details directly into the model's latent representations. This enables the model to perform grounded, multi-step inference entirely in the aligned latent space. Extensive evaluations demonstrate that test-time scaling is effective when incorporating vision knowledge, and that integrating hierarchical information significantly enhances the model's understanding of complex scenes.

Yiming Zhang, Qiangyu Yan, Borui Jiang +1

Nanyang Technological University · Huawei Noah’s Ark Lab

VLM Reasoning Multimodal Large Language Models Latent Visual Reasoning

Feb 5, 2026

Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMs

Multimodal Large Language Models (MLLMs) have shown immense promise in universal multimodal retrieval, which aims to find relevant items of various modalities for a given query. However, their practical application is often hindered by the substantial computational cost incurred from processing a large number of tokens from visual inputs. In this paper, we propose Magic-MM-Embedding, a series of novel models that achieve both high efficiency and state-of-the-art performance in universal multimodal embedding. Our approach is built on two synergistic pillars: (1) a highly efficient MLLM architecture incorporating visual token compression to drastically reduce inference latency and training time, and (2) a multi-stage progressive training strategy designed to not only recover but significantly boost performance. This coarse-to-fine training paradigm begins with extensive continued training to restore multimodal understanding and generation capabilities, progresses to large-scale contrastive pretraining and hard negative mining to enhance discriminative power, and culminates in a task-aware fine-tuning stage guided by an MLLM-as-a-Judge for precise data curation. Comprehensive experiments show that our model outperforms existing methods by a large margin while being more inference-efficient.

Qi Li, Yanzhe Zhao, Yongxin Zhou +4

Honor Device Co., Ltd., China

Efficient Multimodal Inference Multimodal Large Language Models Multimodal Embedding Cross-Modal Retrieval

Feb 4, 2026

DRMOT: A Dataset and Framework for RGBD Referring Multi-Object Tracking

Referring Multi-Object Tracking (RMOT) aims to track specific targets based on language descriptions, playing a vital role in interactive AI systems such as robotics and autonomous driving. However, existing RMOT methods rely exclusively on 2D RGB observations. Since similar 2D projections can correspond to different 3D configurations, the available observations may not uniquely determine the referred targets. This creates a fundamental mismatch between the task requirements and the available input. To advance research on the DRMOT task, we construct DRSet, a dataset tailored for the DRMOT task. DRSet comprises 2,076 referring expressions over 186 RGB-D source sequences. It features synchronized RGB images and depth maps paired with language descriptions, including explicit depth-dependent descriptions, to systematically evaluate spatial-semantic detection and tracking capabilities. Furthermore, we propose DRTrack, an MLLM-guided depth-referring tracking framework. DRTrack leverages a Geometric-Aware GRPO fine-tuned Multimodal Large Language Model (MLLM) to achieve precise spatial-semantic detection from joint L+RGB+D inputs, while incorporating explicit depth cues to enforce robust trajectory association. Extensive experiments on the DRSet dataset demonstrate the effectiveness of our framework. Our dataset and code will be available at https://github.com/chen-si-jia/DRMOT.

Sijia Chen, Shaofeng Liang, Lijuan Ma +7

Huazhong University of Science and Technology · South-Central Minzu University

Referring MOT Multi-Object Tracking Multimodal Large Language Models

Feb 2, 2026

FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding

Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack flexible adaptivity, leading to irreversible detail loss and context fragmentation. To resolve this, we propose FreshMem, a Frequency-Space Hybrid Memory network inspired by the brain's logarithmic perception and memory consolidation. FreshMem reconciles short-term fidelity with long-term coherence through two synergistic modules: Multi-scale Frequency Memory (MFM), which projects overflowing frames into representative frequency coefficients, complemented by residual details to reconstruct a global historical "gist"; and Space Thumbnail Memory (STM), which discretizes the continuous stream into episodic clusters by employing an adaptive compression strategy to distill them into high-density space thumbnails. Extensive experiments show that FreshMem significantly boosts the Qwen2-VL baseline, yielding gains of 5.20%, 4.52%, and 2.34% on StreamingBench, OV-Bench, and OVO-Bench, respectively. As a training-free solution, FreshMem outperforms several fully fine-tuned methods, offering a highly efficient paradigm for long-horizon streaming video understanding.

Kangcong Li, Peng Ye, Lin Zhang +4

College of Future Information Technology, Fudan University, Shanghai, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · The Chinese University of Hong Kong, Hong Kong, China +2

Streaming Video Understanding Memory-Augmented Video Understanding Multimodal Large Language Models

Feb 1, 2026

EEmo-Logic: A Unified Dataset and Multi-Stage Framework for Comprehensive Image-Evoked Emotion Assessment

Understanding the multi-dimensional attributes and intensity nuances of image-evoked emotions is pivotal for advancing machine empathy and empowering diverse human-computer interaction applications. However, existing models are still limited to coarse-grained emotion perception or deficient reasoning capabilities. To bridge this gap, we introduce EEmoDB, the largest image-evoked emotion understanding dataset to date. It features

5

analysis dimensions spanning

5

distinct task categories, facilitating comprehensive interpretation. Specifically, we compile

1.2M

question-answering (QA) pairs (EEmoDB-QA) from

125K

images via automated generation, alongside a

36K

dataset (EEmoDB-Assess) curated from

25K

images for fine-grained assessment. Furthermore, we propose EEmo-Logic, an all-in-one multimodal large language model (MLLM) developed via instruction fine-tuning and task-customized group relative preference optimization (GRPO) with novel reward design. Extensive experiments demonstrate that EEmo-Logic achieves robust performance in in-domain and cross-domain datasets, excelling in emotion QA and fine-grained assessment. The dataset and code are available at https://github.com/workerred/EEmo-Logic.

Lancheng Gao, Ziheng Jia, Zixuan Xing +4

Institute of Image Communication and Network Engineering, Shanghai Key Laboratory of Digital Media Processing and Transmissions, Shanghai Jiao Tong University, Shanghai · School of Communication & Electronic Engineering, East China Normal University, Shanghai

Multimodal Large Language Models Multimodal QA Multimodal Emotion Recognition

Feb 1, 2026

A Multimodal Large Language Model-Driven Framework for Context-Aware UAV Emergency Landing Site Selection

Safe UAV emergency landing requires more than just identifying flat terrain; it demands understanding complex semantic risks (e.g., crowds, temporary structures) invisible to traditional geometric sensors. In this paper, we propose a novel framework leveraging Remote Sensing (RS) imagery and Multimodal Large Language Models (MLLMs) for global context-aware landing site assessment. Unlike local geometric methods, our approach employs a coarse-to-fine pipeline: first, a lightweight semantic segmentation module efficiently pre-screens candidate areas; second, a vision-language reasoning agent fuses visual features with Point-of-Interest (POI) data to detect subtle hazards. To validate this approach, we construct and release the Emergency Landing Site Selection (ELSS) benchmark at https://github.com/chunlianghua/ELSS-dataset. ELSS includes a remote-sensing subset for simulation validation and a UAV aerial-video subset for real-world testing. Experiments demonstrate that our framework significantly outperforms geometric baselines in risk identification accuracy. Furthermore, qualitative results confirm its ability to generate human-like, interpretable justifications, enhancing trust in automated decision-making.

Chunliang Hua, Lei Zhang, Jiayang Sun +2

School of Information Science and Engineering, Southeast University, Nanjing 211189, China · LASER, International Digital Economy Academy, Shenzhen 510085, China · Department of Electronic Engineering, East China Normal University, Shanghai 200241, China

UAV Navigation Multimodal Large Language Models

Feb 1, 2026

MedAD-R1: Consistency-Reinforced Policy Optimization for Interpretable Medical Anomaly Detection

Medical Anomaly Detection (MedAD) offers a promising direction for medical image analysis with Large Multimodal Models (LMMs). However, progress is limited by fragmented datasets and the tendency of Supervised Fine-Tuning (SFT) to learn superficial image-text correlations rather than verifiable diagnostic reasoning. Consequently, current models often generate fluent explanations that are either insufficiently grounded in the image or inconsistent with their final answers, limiting their reliability in high-stakes medical applications. To address these issues, we introduce MedAD-38K, a large-scale, multimodal, and multicenter benchmark containing structured Visual Question Answering pairs and quality-controlled diagnostic Chain-of-Thought annotations across five core MedAD tasks. Based on this benchmark, we propose a two-stage framework. Cognitive Injection first uses SFT to inject domain-specific medical knowledge and establish a structured think-then-answer format. Consistency Group Relative Policy Optimization (Con-GRPO) then employs an Evidence-Aware Consistency Reward to reinforce reasoning that remains grounded in the image and logically supports the final answer. The resulting MedAD-R1 achieves state-of-the-art performance on MedAD-38K and consistently outperforms all evaluated baselines across five source-disjoint external datasets spanning diverse imaging modalities. Beyond accuracy, it achieves higher reasoning-answer consistency and visual-grounding scores across multiple backbones. With only 0.8B parameters, MedAD-R1 offers practical potential for resource-constrained deployment. These results demonstrate the generality of evidence-aware consistency optimization for interpretable MedAD. Project resources are available at https://github.com/zhtstar/MedAD-R1.

Haitao Zhang, Yingying Wang, Jiaxiang Wang +5

School of Informatics, Xiamen University · Institute of Artificial Intelligence, Xiamen University · Zhejiang Expressway Co., Ltd. +3

Healthcare Group Relative Policy Optimization Medical Image Anomaly Detection Multimodal Large Language Models Medical VQA Multimodal Anomaly Detection+2

Jan 30, 2026

TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs

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

Baiqi Li, Kangyi Zhao, Ce Zhang +3

University of North Carolina at Chapel Hill · University of Pittsburgh · Carnegie Mellon University

VLM Evaluation Video Understanding Multimodal Large Language Models Video Reasoning Temporal Video Understanding Multimodal Understanding