{"total":104,"rows":[{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234,"area":"mllm"},{"id":"2408.03326","title":"LLaVA-OneVision: Easy Visual Task Transfer","created":"2024-08-06","cited_by_count":2719,"area":"mllm"},{"id":"2410.02713","title":"LLaVA-Video: Video Instruction Tuning With Synthetic Data","created":"2024-10-03","cited_by_count":583,"area":"mllm"},{"id":"2406.08035","title":"LVBench: An Extreme Long Video Understanding Benchmark","created":"2024-06-12","cited_by_count":410,"area":"mllm"},{"id":"2408.10188","title":"LongVILA: Scaling Long-Context Visual Language Models for Long Videos","created":"2024-08-19","cited_by_count":309,"area":"mllm"},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220,"area":"mllm"},{"id":"2312.14115","title":"LingoQA: Visual Question Answering for Autonomous Driving","created":"2023-12-21","cited_by_count":145,"area":"mllm"},{"id":"2402.03161","title":"Video-LaVIT: Unified Video-Language Pre-training with Decoupled Visual-Motional Tokenization","created":"2024-02-05","cited_by_count":100,"area":"mllm"},{"id":"2408.14023","title":"Video-CCAM: Enhancing Video-Language Understanding with Causal Cross-Attention Masks for Short and Long Videos","created":"2024-08-26","cited_by_count":98,"area":"mllm"},{"id":"2412.10360","title":"Apollo: An Exploration of Video Understanding in Large Multimodal Models","created":"2024-12-13","cited_by_count":89,"area":"mllm"},{"id":"2404.18532","title":"MileBench: Benchmarking MLLMs in Long Context","created":"2024-04-29","cited_by_count":88,"area":"mllm"},{"id":"2509.24871","title":"StreamForest: Efficient Online Video Understanding with Persistent Event Memory","created":"2025-09-29","cited_by_count":78,"area":"mllm"},{"id":"2504.15271","title":"Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models","created":"2025-04-21","cited_by_count":64,"area":"mllm"},{"id":"2406.07230","title":"Needle In A Multimodal Haystack","created":"2024-06-11","cited_by_count":58,"area":"mllm"},{"id":"2502.10810","title":"SVBench: A Benchmark with Temporal Multi-Turn Dialogues for Streaming Video Understanding","created":"2025-02-15","cited_by_count":57,"area":"mllm"},{"id":"2504.08966","title":"PACT: Pruning and Clustering-Based Token Reduction for Faster Visual Language Models","created":"2025-04-11","cited_by_count":49,"area":"mllm"},{"id":"2501.02189","title":"A Survey of State of the Art Large Vision Language Models: Alignment, Benchmark, Evaluations and Challenges","created":"2025-01-04","cited_by_count":47,"area":"mllm"},{"id":"2412.03248","title":"AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruning","created":"2024-12-04","cited_by_count":43,"area":"mllm"},{"id":"2601.14724","title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","created":"2026-01-21","cited_by_count":41,"area":"mllm"},{"id":"2311.14906","title":"AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering","created":"2023-11-25","cited_by_count":40,"area":"mllm"},{"id":"2406.09367","title":"Needle In A Video Haystack: A Scalable Synthetic Evaluator for Video MLLMs","created":"2024-06-13","cited_by_count":37,"area":"mllm"},{"id":"2504.02438","title":"Scaling Video-Language Models to 10K Frames via Hierarchical Differential Distillation","created":"2025-04-03","cited_by_count":37,"area":"mllm"},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2412.09530","title":"Dynamic-VLM: Simple Dynamic Visual Token Compression for VideoLLM","created":"2024-12-12","cited_by_count":32,"area":"mllm"},{"id":"2504.10068","title":"Mavors: Multi-granularity Video Representation for Multimodal Large Language Model","created":"2025-04-14","cited_by_count":32,"area":"mllm"},{"id":"2503.12772","title":"NuPlanQA: A Large-Scale Dataset and Benchmark for Multi-View Driving Scene Understanding in Multi-Modal Large Language Models","created":"2025-03-17","cited_by_count":30,"area":"mllm"},{"id":"2506.03340","title":"Seeing the Arrow of Time in Large Multimodal Models","created":"2025-06-03","cited_by_count":30,"area":"mllm"},{"id":"2412.19326","title":"Task Preference Optimization: Improving Multimodal Large Language Models with Vision Task Alignment","created":"2024-12-26","cited_by_count":29,"area":"mllm"},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2503.13956","title":"Improving LLM Video Understanding with 16 Frames Per Second","created":"2025-03-18","cited_by_count":26,"area":"mllm"},{"id":"2504.16083","title":"MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention","created":"2025-04-22","cited_by_count":26,"area":"mllm"},{"id":"2404.01476","title":"TraveLER: A Modular Multi-LMM Agent Framework for Video Question-Answering","created":"2024-04-01","cited_by_count":25,"area":"mllm"},{"id":"2412.09613","title":"PVC: Progressive Visual Token Compression for Unified Image and Video Processing in Large Vision-Language Models","created":"2024-12-12","cited_by_count":25,"area":"mllm"},{"id":"2507.20198","title":"A Survey of Token Compression for Efficient Multimodal Large Language Models","created":"2025-07-27","cited_by_count":25,"area":"mllm"},{"id":"2412.08646","title":"StreamChat: Chatting with Streaming Video","created":"2024-12-11","cited_by_count":24,"area":"mllm"},{"id":"2506.05332","title":"Unleashing Hour-Scale Video Training for Long Video-Language Understanding","created":"2025-06-05","cited_by_count":23,"area":"mllm"},{"id":"2506.05287","title":"EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?","created":"2025-06-05","cited_by_count":21,"area":"mllm"},{"id":"2411.13281","title":"VideoAutoArena: An Automated Arena for Evaluating Large Multimodal Models in Video Analysis through User Simulation","created":"2024-11-20","cited_by_count":18,"area":"mllm"},{"id":"2503.10742","title":"Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing","created":"2025-03-13","cited_by_count":18,"area":"mllm"},{"id":"2510.04401","title":"Your Vision-Language Model Can't Even Count to 20: Exposing the Failures of VLMs in Compositional Counting","created":"2025-10-06","cited_by_count":18,"area":"mllm"},{"id":"2506.01274","title":"ReFoCUS: Reinforcement-guided Frame Optimization for Contextual Understanding","created":"2025-06-02","cited_by_count":16,"area":"mllm"},{"id":"2407.08583","title":"The Synergy between Data and Multi-Modal Large Language Models: A Survey from Co-Development Perspective","created":"2024-07-11","cited_by_count":15,"area":"mllm"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2509.14033","title":"SAIL-VL2 Technical Report","created":"2025-09-17","cited_by_count":14,"area":"mllm"},{"id":"2512.22748","title":"TrimTokenator-LC: Towards Adaptive Visual Token Pruning for Large Multimodal Models with Long Contexts","created":"2025-12-28","cited_by_count":14,"area":"mllm"},{"id":"2406.10215","title":"DevBench: A multimodal developmental benchmark for language learning","created":"2024-06-14","cited_by_count":13,"area":"mllm"},{"id":"2411.16173","title":"SALOVA: Segment-Augmented Long Video Assistant for Targeted Retrieval and Routing in Long-Form Video Analysis","created":"2024-11-25","cited_by_count":13,"area":"mllm"},{"id":"2510.08559","title":"SciVideoBench: Benchmarking Scientific Video Reasoning in Large Multimodal Models","created":"2025-10-09","cited_by_count":13,"area":"mllm"},{"id":"2505.20715","title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","created":"2025-05-27","cited_by_count":12,"area":"mllm"},{"id":"2506.07016","title":"MAGNET: A Multi-agent Framework for Finding Audio-Visual Needles by Reasoning over Multi-Video Haystacks","created":"2025-06-08","cited_by_count":12,"area":"mllm"},{"id":"2412.19794","title":"MVTamperBench: Evaluating Robustness of Vision-Language Models","created":"2024-12-27","cited_by_count":11,"area":"mllm"},{"id":"2503.17736","title":"V2P-Bench: Evaluating Video-Language Understanding with Visual Prompts for Better Human-Model Interaction","created":"2025-03-22","cited_by_count":11,"area":"mllm"},{"id":"2503.22610","title":"Evaluating Multimodal Language Models as Visual Assistants for Visually Impaired Users","created":"2025-03-28","cited_by_count":11,"area":"mllm"},{"id":"2504.03970","title":"VideoComp: Advancing Fine-Grained Compositional and Temporal Alignment in Video-Text Models","created":"2025-04-04","cited_by_count":11,"area":"mllm"},{"id":"2505.17020","title":"CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms","created":"2025-05-22","cited_by_count":11,"area":"mllm"},{"id":"2510.13891","title":"K-frames: Scene-Driven Any-k Keyframe Selection for long video understanding","created":"2025-10-14","cited_by_count":11,"area":"mllm"},{"id":"2501.05067","title":"LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding","created":"2025-01-09","cited_by_count":10,"area":"mllm"},{"id":"2504.01328","title":"Slow-Fast Architecture for Video Multi-Modal Large Language Models","created":"2025-04-02","cited_by_count":10,"area":"mllm"},{"id":"2504.07454","title":"How Can Objects Help Video-Language Understanding?","created":"2025-04-10","cited_by_count":8,"area":"mllm"},{"id":"2512.03963","title":"TempR1: Improving Temporal Understanding of MLLMs via Temporal-Aware Multi-Task Reinforcement Learning","created":"2025-12-03","cited_by_count":8,"area":"mllm"},{"id":"2503.19356","title":"Can Vision-Language Models Answer Face to Face Questions in the Real-World?","created":"2025-03-25","cited_by_count":7,"area":"mllm"},{"id":"2504.18152","title":"ActionArt: Advancing Multimodal Large Models for Fine-Grained Human-Centric Video Understanding","created":"2025-04-25","cited_by_count":7,"area":"mllm"},{"id":"2510.03584","title":"FrameOracle: Learning What to See and How Much to See in Videos","created":"2025-10-04","cited_by_count":7,"area":"mllm"},{"id":"2603.06569","title":"Penguin-VL: Exploring the Efficiency Limits of VLM with LLM-based Vision Encoders","created":"2026-03-06","cited_by_count":7,"area":"mllm"},{"id":"2503.08576","title":"RAG-Adapter: A Plug-and-Play RAG-enhanced Framework for Long Video Understanding","created":"2025-03-11","cited_by_count":6,"area":"mllm"},{"id":"2506.07032","title":"A Culturally-diverse Multilingual Multimodal Video Benchmark & Model","created":"2025-06-08","cited_by_count":5,"area":"mllm"},{"id":"2503.03840","title":"Decoupling the components of geometric understanding in Vision Language Models","created":"2025-03-05","cited_by_count":4,"area":"mllm"},{"id":"2503.18712","title":"LLaVAction: evaluating and training multi-modal large language models for action understanding","created":"2025-03-24","cited_by_count":3,"area":"mllm"},{"id":"2505.18855","title":"Inference Compute-Optimal Video Vision Language Models","created":"2025-05-24","cited_by_count":3,"area":"mllm"},{"id":"2601.21666","title":"SONIC-O1: A Real-World Benchmark for Evaluating Multimodal Large Language Models on Audio-Video Understanding","created":"2026-01-29","cited_by_count":3,"area":"mllm"},{"id":"2602.17869","title":"Learning Compact Video Representations for Efficient Long-form Video Understanding in Large Multimodal Models","created":"2026-02-19","cited_by_count":3,"area":"mllm"},{"id":"2602.22142","title":"WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMs","created":"2026-02-25","cited_by_count":3,"area":"mllm"},{"id":"2603.08436","title":"Can Vision-Language Models Solve the Shell Game?","created":"2026-03-09","cited_by_count":3,"area":"mllm"},{"id":"2502.20811","title":"HAIC: Improving Human Action Understanding and Generation with Better Captions for Multi-modal Large Language Models","created":"2025-02-28","cited_by_count":2,"area":"mllm"},{"id":"2505.10541","title":"Exploring Implicit Visual Misunderstandings in Multimodal Large Language Models through Attention Analysis","created":"2025-05-15","cited_by_count":2,"area":"mllm"},{"id":"2507.23382","title":"MPCC: A Novel Benchmark for Multimodal Planning with Complex Constraints in Multimodal Large Language Models","created":"2025-07-31","cited_by_count":2,"area":"mllm"},{"id":"2509.14227","title":"Cin\\'{e}aste: A Fine-grained Contextual Movie Question Answering Benchmark","created":"2025-09-17","cited_by_count":2,"area":"mllm"},{"id":"2512.11336","title":"UFVideo: Towards Unified Fine-Grained Video Cooperative Understanding with Large Language Models","created":"2025-12-12","cited_by_count":2,"area":"mllm"},{"id":"2505.12746","title":"Correspondence of high-dimensional emotion structures elicited by video clips between humans and Multimodal LLMs","created":"2025-05-19","cited_by_count":1,"area":"mllm"},{"id":"2505.19125","title":"RTime-QA: A Benchmark for Atomic Temporal Event Understanding in Large Multi-modal Models","created":"2025-05-25","cited_by_count":1,"area":"mllm"},{"id":"2507.02904","title":"Enhancing Sports Strategy with Video Analytics and Data Mining: Assessing the effectiveness of Multimodal LLMs in tennis video analysis","created":"2025-06-24","cited_by_count":1,"area":"mllm"},{"id":"2507.21420","title":"ReGATE: Learning Faster and Better with Fewer Tokens in MLLMs","created":"2025-07-29","cited_by_count":1,"area":"mllm"},{"id":"2512.19535","title":"CASA: Cross-Attention over Self-Attention for Efficient Vision-Language Fusion","created":"2025-12-22","cited_by_count":1,"area":"mllm"},{"id":"2602.07790","title":"MaD-Mix: Multi-Modal Data Mixtures via Latent Space Coupling for Vision-Language Model Training","created":"2026-02-08","cited_by_count":1,"area":"mllm"},{"id":"2603.18004","title":"Unified Spatio-Temporal Token Scoring for Efficient Video VLMs","created":"2026-03-18","cited_by_count":1,"area":"mllm"},{"id":"2604.07634","title":"VSAS-Bench: Real-Time Evaluation of Visual Streaming Assistant Models","created":"2026-04-08","cited_by_count":1,"area":"mllm"},{"id":"2604.23407","title":"PushupBench: Your VLM is not good at counting pushups","created":"2026-04-25","cited_by_count":1,"area":"mllm"},{"id":"2605.22109","title":"Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?","created":"2026-05-21","cited_by_count":1,"area":"mllm"},{"id":"2608.20414","title":"StateSight: Benchmarking Latent Spatial-State Reconstruction in Vision-Language Models","created":"2026-08-15","cited_by_count":1,"area":"mllm"},{"id":"2608.27881","title":"StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2411.08840","title":"Multimodal Instruction Tuning with Hybrid State Space Models","created":"2024-11-13","cited_by_count":0,"area":"mllm"},{"id":"2504.12315","title":"Capybara-OMNI: An Efficient Paradigm for Building Omni-Modal Language Models","created":"2025-04-10","cited_by_count":0,"area":"mllm"},{"id":"2505.15529","title":"Clapper: Compact Learning and Video Representation in VLMs","created":"2025-05-21","cited_by_count":0,"area":"mllm"},{"id":"2507.10302","title":"DisCo: Towards Distinct and Coherent Visual Encapsulation in Video MLLMs","created":"2025-07-14","cited_by_count":0,"area":"mllm"},{"id":"2511.02182","title":"Pinpointing Trigger Moment for Grounded Video QA: Enhancing Spatio-temporal Grounding in Multimodal Large Language Models","created":"2025-11-04","cited_by_count":0,"area":"mllm"},{"id":"2604.11136","title":"BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-Tuning","created":"2026-04-13","cited_by_count":0,"area":"mllm"},{"id":"2605.08158","title":"HY-Himmel Technical Report: Hierarchical Interleaved Multi-stream Motion Encoding for Long Video Understanding","created":"2026-05-04","cited_by_count":0,"area":"mllm"},{"id":"2606.05748","title":"UNIVID: Unified Vision-Language Model for Video Moderation","created":"2026-06-04","cited_by_count":0,"area":"mllm"},{"id":"2607.09029","title":"MOSAIC: Adaptive Inter-layer Composition for Efficient Heterogeneous Vision-Language Models","created":"2026-07-10","cited_by_count":0,"area":"mllm"},{"id":"2608.03112","title":"Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models","created":"2026-08-04","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}