{"total":292,"rows":[{"id":"2412.05271","title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","created":"2024-12-06","cited_by_count":1599,"area":"lr"},{"id":"2406.07476","title":"VideoLLaMA 2: Advancing Spatial-Temporal Modeling and Audio Understanding in Video-LLMs","created":"2024-06-11","cited_by_count":771,"area":null},{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497,"area":null},{"id":"2410.17434","title":"LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding","created":"2024-10-22","cited_by_count":356,"area":"mllm"},{"id":"2407.03320","title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","created":"2024-07-03","cited_by_count":195,"area":"mllm"},{"id":"2509.18154","title":"MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe","created":"2025-09-16","cited_by_count":186,"area":"mllm"},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174,"area":"moe"},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155,"area":"mllm"},{"id":"2411.03628","title":"StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding","created":"2024-11-06","cited_by_count":144,"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":"2508.09736","title":"Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory","created":"2025-08-13","cited_by_count":97,"area":"agents"},{"id":"2503.03803","title":"EgoLife: Towards Egocentric Life Assistant","created":"2025-03-05","cited_by_count":91,"area":null},{"id":"2412.12075","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","created":"2024-12-16","cited_by_count":85,"area":"mllm"},{"id":"2504.02259","title":"T*: Re-thinking Temporal Search for Long-Form Video Understanding","created":"2025-04-03","cited_by_count":82,"area":"lr"},{"id":"2501.07888","title":"Tarsier2: Advancing Large Vision-Language Models from Detailed Video Description to Comprehensive Video Understanding","created":"2025-01-14","cited_by_count":81,"area":"mllm"},{"id":"2604.27393","title":"MiniCPM-o 4.5: Towards Real-Time Full-Duplex Omni-Modal Interaction","created":"2026-04-30","cited_by_count":78,"area":"mllm"},{"id":"2410.23266","title":"TOMATO: Assessing Visual Temporal Reasoning Capabilities in Multimodal Foundation Models","created":"2024-10-30","cited_by_count":73,"area":"lr"},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72,"area":"mllm"},{"id":"2411.18211","title":"TimeMarker: A Versatile Video-LLM for Long and Short Video Understanding with Superior Temporal Localization Ability","created":"2024-11-27","cited_by_count":70,"area":"mllm"},{"id":"2508.15717","title":"StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding","created":"2025-08-21","cited_by_count":58,"area":"mllm"},{"id":"2412.09596","title":"InternLM-XComposer2.5-OmniLive: A Comprehensive Multimodal System for Long-term Streaming Video and Audio Interactions","created":"2024-12-12","cited_by_count":48,"area":"mllm"},{"id":"2606.13392","title":"MiniMax Sparse Attention","created":"2026-06-11","cited_by_count":44,"area":"lr"},{"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":"2510.18269","title":"StreamingTOM: Streaming Token Compression for Efficient Video Understanding","created":"2025-10-21","cited_by_count":43,"area":"mllm"},{"id":"2504.07956","title":"VCR-Bench: A Comprehensive Evaluation Framework for Video Chain-of-Thought Reasoning","created":"2025-04-10","cited_by_count":42,"area":"lr"},{"id":"2410.06166","title":"Temporal Reasoning Transfer from Text to Video","created":"2024-10-08","cited_by_count":38,"area":"lr"},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37,"area":"rag"},{"id":"2510.27280","title":"FOCUS: Efficient Keyframe Selection for Long Video Understanding","created":"2025-10-31","cited_by_count":37,"area":"mllm"},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"},{"id":"2507.06485","title":"Video-RTS: Rethinking Reinforcement Learning and Test-Time Scaling for Efficient and Enhanced Video Reasoning","created":"2025-07-09","cited_by_count":33,"area":"lr"},{"id":"2604.02317","title":"A Simple Baseline for Streaming Video Understanding","created":"2026-04-02","cited_by_count":33,"area":null},{"id":"2507.07990","title":"Multi-Granular Spatio-Temporal Token Merging for Training-Free Acceleration of Video LLMs","created":"2025-07-10","cited_by_count":31,"area":"inference"},{"id":"2510.14032","title":"Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding","created":"2025-10-15","cited_by_count":31,"area":"lr"},{"id":"2409.18938","title":"From Seconds to Hours: Reviewing MultiModal Large Language Models on Comprehensive Long Video Understanding","created":"2024-09-27","cited_by_count":30,"area":"lr"},{"id":"2603.02096","title":"FluxMem: Adaptive Hierarchical Memory for Streaming Video Understanding","created":"2026-03-02","cited_by_count":28,"area":null},{"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":"2512.22315","title":"VideoZoomer: Reinforcement-Learned Temporal Focusing for Long Video Reasoning","created":"2025-12-26","cited_by_count":27,"area":"lr"},{"id":"2506.05349","title":"VideoMathQA: Benchmarking Mathematical Reasoning via Multimodal Understanding in Videos","created":"2025-06-05","cited_by_count":25,"area":"lr"},{"id":"2410.08474","title":"SPORTU: A Comprehensive Sports Understanding Benchmark for Multimodal Large Language Models","created":"2024-10-11","cited_by_count":24,"area":"mllm"},{"id":"2506.10857","title":"VRBench: A Benchmark for Multi-Step Reasoning in Long Narrative Videos","created":"2025-06-12","cited_by_count":24,"area":"lr"},{"id":"2507.15028","title":"Towards Video Thinking Test: A Holistic Benchmark for Advanced Video Reasoning and Understanding","created":"2025-07-20","cited_by_count":24,"area":"lr"},{"id":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24,"area":null},{"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":"2412.00161","title":"STEP: Enhancing Video-LLMs' Compositional Reasoning by Spatio-Temporal Graph-guided Self-Training","created":"2024-11-29","cited_by_count":22,"area":"lr"},{"id":"2506.04141","title":"MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos","created":"2025-06-04","cited_by_count":22,"area":"lr"},{"id":"2511.16668","title":"V-ReasonBench: Toward Unified Reasoning Benchmark Suite for Video Generation Models","created":"2025-11-20","cited_by_count":22,"area":"lr"},{"id":"2505.15804","title":"STAR-R1: Spatial TrAnsformation Reasoning by Reinforcing Multimodal LLMs","created":"2025-05-21","cited_by_count":21,"area":"lr"},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21,"area":null},{"id":"2412.05185","title":"LinVT: Empower Your Image-level Large Language Model to Understand Videos","created":"2024-12-06","cited_by_count":19,"area":null},{"id":"2506.00993","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","created":"2025-06-01","cited_by_count":18,"area":null},{"id":"2602.08024","title":"FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging","created":"2026-02-08","cited_by_count":18,"area":"inference"},{"id":"2510.17777","title":"SparseVILA: Decoupling Visual Sparsity for Efficient VLM Inference","created":"2025-10-20","cited_by_count":15,"area":"mllm"},{"id":"2603.01455","title":"From Verbatim to Gist: Distilling Pyramidal Multimodal Memory via Semantic Information Bottleneck for Long-Horizon Video Agents","created":"2026-03-02","cited_by_count":15,"area":"lr"},{"id":"2603.28069","title":"MolmoPoint: Better Pointing for VLMs with Grounding Tokens","created":"2026-03-30","cited_by_count":15,"area":"mllm"},{"id":"2505.21233","title":"CROP: Contextual Region-Oriented Visual Token Pruning","created":"2025-05-27","cited_by_count":14,"area":"inference"},{"id":"2503.19355","title":"ST-VLM: Kinematic Instruction Tuning for Spatio-Temporal Reasoning in Vision-Language Models","created":"2025-03-25","cited_by_count":13,"area":"lr"},{"id":"2505.24164","title":"Mixed-R1: Unified Reward Perspective For Reasoning Capability in Multimodal Large Language Models","created":"2025-05-30","cited_by_count":13,"area":"lr"},{"id":"2603.16859","title":"SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models","created":"2026-03-17","cited_by_count":13,"area":null},{"id":"2505.19000","title":"VerIPO: Cultivating Long Reasoning in Video-LLMs via Verifier-Gudied Iterative Policy Optimization","created":"2025-05-25","cited_by_count":12,"area":"lr"},{"id":"2602.03060","title":"IVC-Prune: Revealing the Implicit Visual Coordinates in LVLMs for Vision Token Pruning","created":"2026-02-03","cited_by_count":12,"area":"mllm"},{"id":"2412.17574","title":"HumanVBench: Probing Human-Centric Video Understanding in MLLMs with Automatically Synthesized Benchmarks","created":"2024-12-23","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":"2512.04000","title":"Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding","created":"2025-12-03","cited_by_count":11,"area":"mllm"},{"id":"2602.00288","title":"TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs","created":"2026-01-30","cited_by_count":11,"area":null},{"id":"2512.23044","title":"Video-Browser: Towards Agentic Open-web Video Browsing","created":"2025-12-28","cited_by_count":10,"area":"agents"},{"id":"2607.24904","title":"Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model","created":"2026-07-27","cited_by_count":10,"area":"lr"},{"id":"2411.11066","title":"TS-LLaVA: Constructing Visual Tokens through Thumbnail-and-Sampling for Training-Free Video Large Language Models","created":"2024-11-17","cited_by_count":9,"area":"mllm"},{"id":"2507.16878","title":"CausalStep: A Benchmark for Explicit Stepwise Causal Reasoning in Videos","created":"2025-07-22","cited_by_count":9,"area":"lr"},{"id":"2510.17364","title":"Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs","created":"2025-10-20","cited_by_count":9,"area":null},{"id":"2508.07470","title":"AURA: A Fine-Grained Benchmark and Decomposed Metric for Audio-Visual Reasoning","created":"2025-08-10","cited_by_count":8,"area":"lr"},{"id":"2602.16412","title":"ReMoRa: Multimodal Large Language Model based on Refined Motion Representation for Long-Video Understanding","created":"2026-02-18","cited_by_count":8,"area":"mllm"},{"id":"2603.25072","title":"GIFT: Global Irreplaceability Frame Targeting for Efficient Video Understanding","created":"2026-03-26","cited_by_count":8,"area":null},{"id":"2505.18757","title":"ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance","created":"2025-05-24","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":"2510.17722","title":"MT-Video-Bench: A Holistic Video Understanding Benchmark for Evaluating Multimodal LLMs in Multi-Turn Dialogues","created":"2025-10-20","cited_by_count":7,"area":"mllm"},{"id":"2512.03575","title":"UniComp: Rethinking Video Compression Through Informational Uniqueness","created":"2025-12-03","cited_by_count":7,"area":null},{"id":"2601.13836","title":"FutureOmni: Evaluating Future Forecasting from Omni-Modal Context for Multimodal LLMs","created":"2026-01-20","cited_by_count":7,"area":"mllm"},{"id":"2602.04094","title":"VideoBrain: Learning Adaptive Frame Sampling for Long Video Understanding","created":"2026-02-04","cited_by_count":7,"area":"mllm"},{"id":"2602.07801","title":"VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos","created":"2026-02-08","cited_by_count":7,"area":"agents"},{"id":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2603.18472","title":"Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding","created":"2026-03-19","cited_by_count":7,"area":"mllm"},{"id":"2604.01569","title":"VideoZeroBench: Probing the Limits of Video MLLMs with Spatio-Temporal Evidence Verification","created":"2026-04-02","cited_by_count":7,"area":"mllm"},{"id":"2605.14906","title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","created":"2026-05-14","cited_by_count":7,"area":"mllm"},{"id":"2605.27705","title":"AgenticVBench: Can AI Agents Complete Real-World Post-Production Tasks?","created":"2026-05-26","cited_by_count":7,"area":"agents"},{"id":"2606.02569","title":"AdaCodec: A Predictive Visual Code for Video MLLMs","created":"2026-06-01","cited_by_count":7,"area":null},{"id":"2606.16353","title":"What Should a Streaming Video Model Remember?","created":"2026-06-15","cited_by_count":7,"area":null},{"id":"2410.13694","title":"Exploring the Design Space of Visual Context Representation in Video MLLMs","created":"2024-10-17","cited_by_count":6,"area":"mllm"},{"id":"2508.19650","title":"Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models","created":"2025-08-27","cited_by_count":6,"area":null},{"id":"2509.23724","title":"Video Panels for Long Video Understanding","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2512.10324","title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","created":"2025-12-11","cited_by_count":6,"area":"inference"},{"id":"2602.03615","title":"KTV: Keyframes and Key Tokens Selection for Efficient Training-Free Video LLMs","created":"2026-02-03","cited_by_count":6,"area":"mllm"},{"id":"2603.12703","title":"SVCBench: A Streaming Video Counting Benchmark for Spatial-Temporal State Maintenance","created":"2026-03-13","cited_by_count":6,"area":null},{"id":"2603.21957","title":"Unified Spatiotemporal Token Compression for Video-LLMs at Ultra-Low Retention","created":"2026-03-23","cited_by_count":6,"area":"inference"},{"id":"2604.05418","title":"VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG","created":"2026-04-07","cited_by_count":6,"area":"mllm"},{"id":"2605.20342","title":"ParaVT: Taming the Tool Prior Paradox for Parallel Tool Use in Agentic Video Reinforcement Learning","created":"2026-05-19","cited_by_count":6,"area":"mllm"},{"id":"2605.22269","title":"MuKV: Multi-Grained KV Cache Compression for Long Streaming Video Question-Answering","created":"2026-05-21","cited_by_count":6,"area":"lr"},{"id":"2606.24422","title":"EgoSAT: A Comprehensive Benchmark of Egocentric Streaming Interaction Understanding","created":"2026-06-23","cited_by_count":6,"area":"mllm"},{"id":"2505.08455","title":"VCRBench: Exploring Long-form Causal Reasoning Capabilities of Large Video Language Models","created":"2025-05-13","cited_by_count":5,"area":"lr"},{"id":"2509.26360","title":"TimeScope: Towards Task-Oriented Temporal Grounding In Long Videos","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2510.20622","title":"SeViCES: Unifying Semantic-Visual Evidence Consensus for Long Video Understanding","created":"2025-10-23","cited_by_count":5,"area":null}],"next_cursor":"100"}