{"total":213,"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":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413,"area":"mllm"},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584,"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":"2406.16852","title":"Long Context Transfer from Language to Vision","created":"2024-06-24","cited_by_count":515,"area":"mllm"},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326,"area":null},{"id":"2406.04264","title":"MLVU: Benchmarking Multi-task Long Video Understanding","created":"2024-06-06","cited_by_count":292,"area":null},{"id":"2505.15966","title":"Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learning","created":"2025-05-21","cited_by_count":278,"area":"lr"},{"id":"2405.19209","title":"VideoTree: Adaptive Tree-based Video Representation for LLM Reasoning on Long Videos","created":"2024-05-29","cited_by_count":251,"area":"lr"},{"id":"2506.23918","title":"Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers","created":"2025-06-30","cited_by_count":199,"area":"lr"},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2501.05510","title":"OVO-Bench: How Far is Your Video-LLMs from Real-World Online Video Understanding?","created":"2025-01-09","cited_by_count":142,"area":null},{"id":"2501.12380","title":"MMVU: Measuring Expert-Level Multi-Discipline Video Understanding","created":"2025-01-21","cited_by_count":137,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2505.17862","title":"Daily-Omni: Towards Audio-Visual Reasoning with Temporal Alignment across Modalities","created":"2025-05-23","cited_by_count":110,"area":"lr"},{"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":"2412.12075","title":"CG-Bench: Clue-grounded Question Answering Benchmark for Long Video Understanding","created":"2024-12-16","cited_by_count":85,"area":"mllm"},{"id":"2507.07966","title":"Scaling RL to Long Videos","created":"2025-07-10","cited_by_count":84,"area":"lr"},{"id":"2410.03226","title":"Frame-Voyager: Learning to Query Frames for Video Large Language Models","created":"2024-10-04","cited_by_count":83,"area":null},{"id":"2410.08202","title":"Mono-InternVL: Pushing the Boundaries of Monolithic Multimodal Large Language Models with Endogenous Visual Pre-training","created":"2024-10-10","cited_by_count":82,"area":"mllm"},{"id":"2409.20566","title":"MM1.5: Methods, Analysis & Insights from Multimodal LLM Fine-tuning","created":"2024-09-30","cited_by_count":76,"area":"mllm"},{"id":"2409.18111","title":"E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding","created":"2024-09-26","cited_by_count":70,"area":null},{"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":"2501.00584","title":"Online Video Understanding: OVBench and VideoChat-Online","created":"2024-12-31","cited_by_count":61,"area":"mllm"},{"id":"2501.08282","title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","created":"2025-01-14","cited_by_count":59,"area":"mllm"},{"id":"2503.22952","title":"OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts","created":"2025-03-29","cited_by_count":51,"area":"mllm"},{"id":"2510.20579","title":"Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence","created":"2025-10-23","cited_by_count":49,"area":"lr"},{"id":"2408.14469","title":"Grounded Multi-Hop VideoQA in Long-Form Egocentric Videos","created":"2024-08-26","cited_by_count":45,"area":null},{"id":"2406.08407","title":"MMWorld: Towards Multi-discipline Multi-faceted World Model Evaluation in Videos","created":"2024-06-12","cited_by_count":43,"area":"wm"},{"id":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42,"area":null},{"id":"2509.24304","title":"FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting","created":"2025-09-29","cited_by_count":42,"area":"lr"},{"id":"2410.12332","title":"MC-Bench: A Benchmark for Multi-Context Visual Grounding in the Era of MLLMs","created":"2024-10-16","cited_by_count":39,"area":"mllm"},{"id":"2412.01694","title":"Enhancing Video-LLM Reasoning via Agent-of-Thoughts Distillation","created":"2024-12-02","cited_by_count":37,"area":"lr"},{"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":"2406.06467","title":"How Far Can Transformers Reason? The Globality Barrier and Inductive Scratchpad","created":"2024-06-10","cited_by_count":36,"area":null},{"id":"2503.06157","title":"UrbanVideo-Bench: Benchmarking Vision-Language Models on Embodied Intelligence with Video Data in Urban Spaces","created":"2025-03-08","cited_by_count":36,"area":"mllm"},{"id":"2405.19334","title":"LLMs Meet Multimodal Generation and Editing: A Survey","created":"2024-05-29","cited_by_count":35,"area":null},{"id":"2510.23473","title":"Video-Thinker: Sparking \"Thinking with Videos\" via Reinforcement Learning","created":"2025-10-27","cited_by_count":34,"area":"lr"},{"id":"2406.07544","title":"Situational Awareness Matters in 3D Vision Language Reasoning","created":"2024-06-11","cited_by_count":33,"area":null},{"id":"2506.23270","title":"Token Activation Map to Visually Explain Multimodal LLMs","created":"2025-06-29","cited_by_count":32,"area":"mllm"},{"id":"2505.24718","title":"Reinforcing Video Reasoning with Focused Thinking","created":"2025-05-30","cited_by_count":31,"area":"lr"},{"id":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"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":"2407.06189","title":"Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision","created":"2024-07-08","cited_by_count":25,"area":"mllm"},{"id":"2412.09582","title":"Neptune: The Long Orbit to Benchmarking Long Video Understanding","created":"2024-12-12","cited_by_count":25,"area":null},{"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":"2503.09590","title":"BIMBA: Selective-Scan Compression for Long-Range Video Question Answering","created":"2025-03-12","cited_by_count":24,"area":null},{"id":"2503.14935","title":"FAVOR-Bench: A Comprehensive Benchmark for Fine-Grained Video Motion Understanding","created":"2025-03-19","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":"2506.21876","title":"Do Vision-Language Models Have Internal World Models? Towards an Atomic Evaluation","created":"2025-06-27","cited_by_count":24,"area":"wm"},{"id":"2504.03151","title":"Why Reasoning Matters? A Survey of Advancements in Multimodal Reasoning (v1)","created":"2025-04-04","cited_by_count":23,"area":"lr"},{"id":"2511.15722","title":"Spatial Reasoning in Multimodal Large Language Models: A Survey of Tasks, Benchmarks and Methods","created":"2025-11-14","cited_by_count":23,"area":"lr"},{"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":"2412.01800","title":"PhysGame: Uncovering Physical Commonsense Violations in Gameplay Videos","created":"2024-12-02","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2509.07447","title":"In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting","created":"2025-09-09","cited_by_count":22,"area":"mllm"},{"id":"2406.14129","title":"Towards Event-oriented Long Video Understanding","created":"2024-06-20","cited_by_count":21,"area":"mllm"},{"id":"2509.24008","title":"FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning","created":"2025-09-28","cited_by_count":21,"area":null},{"id":"2512.19526","title":"QuantiPhy: A Quantitative Benchmark Evaluating Physical Reasoning Abilities of Vision-Language Models","created":"2025-12-22","cited_by_count":20,"area":"lr"},{"id":"2407.15047","title":"End-to-End Video Question Answering with Frame Scoring Mechanisms and Adaptive Sampling","created":"2024-07-21","cited_by_count":19,"area":null},{"id":"2502.18778","title":"M2-omni: Advancing Omni-MLLM for Comprehensive Modality Support with Competitive Performance","created":"2025-02-26","cited_by_count":19,"area":null},{"id":"2406.00622","title":"Compositional 4D Dynamic Scenes Understanding with Physics Priors for Video Question Answering","created":"2024-06-02","cited_by_count":18,"area":"mllm"},{"id":"2407.08101","title":"What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction","created":"2024-07-11","cited_by_count":18,"area":"mllm"},{"id":"2510.23095","title":"Revisiting Multimodal Positional Encoding in Vision-Language Models","created":"2025-10-27","cited_by_count":16,"area":"mllm"},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2508.01699","title":"TimeExpert: An Expert-Guided Video LLM for Video Temporal Grounding","created":"2025-08-03","cited_by_count":14,"area":"moe"},{"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":"2407.20962","title":"MMTrail: A Multimodal Trailer Video Dataset with Language and Music Descriptions","created":"2024-07-30","cited_by_count":13,"area":null},{"id":"2411.14401","title":"Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding","created":"2024-11-21","cited_by_count":13,"area":"mllm"},{"id":"2507.00469","title":"Bisecle: Binding and Separation in Continual Learning for Video Language Understanding","created":"2025-07-01","cited_by_count":13,"area":"mllm"},{"id":"2507.12566","title":"Mono-InternVL-1.5: Towards Cheaper and Faster Monolithic Multimodal Large Language Models","created":"2025-07-16","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":"2605.09874","title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","created":"2026-05-11","cited_by_count":13,"area":"lr"},{"id":"2406.10221","title":"Long Story Short: Story-level Video Understanding from 20K Short Films","created":"2024-06-14","cited_by_count":12,"area":"mllm"},{"id":"2412.04652","title":"Cross-Self KV Cache Pruning for Efficient Vision-Language Inference","created":"2024-12-05","cited_by_count":12,"area":"inference"},{"id":"2503.07635","title":"Cross-modal Causal Relation Alignment for Video Question Grounding","created":"2025-03-05","cited_by_count":12,"area":null},{"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":"2506.15724","title":"MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference","created":"2025-06-06","cited_by_count":12,"area":"mllm"},{"id":"2406.02106","title":"MARS: Benchmarking the Metaphysical Reasoning Abilities of Language Models with a Multi-task Evaluation Dataset","created":"2024-06-04","cited_by_count":11,"area":"lr"},{"id":"2410.08126","title":"Mars: Situated Inductive Reasoning in an Open-World Environment","created":"2024-10-10","cited_by_count":11,"area":"lr"},{"id":"2410.14248","title":"Addressing Blind Guessing: Calibration of Selection Bias in Multiple-Choice Question Answering by Video Language Models","created":"2024-10-18","cited_by_count":11,"area":null},{"id":"2412.19794","title":"MVTamperBench: Evaluating Robustness of Vision-Language Models","created":"2024-12-27","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":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2405.18831","title":"Evaluating Zero-Shot GPT-4V Performance on 3D Visual Question Answering Benchmarks","created":"2024-05-29","cited_by_count":10,"area":null},{"id":"2406.10889","title":"VELOCITI: Benchmarking Video-Language Compositional Reasoning with Strict Entailment","created":"2024-06-16","cited_by_count":10,"area":"lr"},{"id":"2412.16158","title":"HoVLE: Unleashing the Power of Monolithic Vision-Language Models with Holistic Vision-Language Embedding","created":"2024-12-20","cited_by_count":10,"area":"mllm"},{"id":"2504.05046","title":"MotionPRO: Exploring the Role of Pressure in Human MoCap and Beyond","created":"2025-04-07","cited_by_count":10,"area":null},{"id":"2511.07250","title":"MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs","created":"2025-11-10","cited_by_count":10,"area":"mllm"},{"id":"2406.09646","title":"A Survey of Video Datasets for Grounded Event Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2501.07214","title":"TimeLogic: A Temporal Logic Benchmark for Video QA","created":"2025-01-13","cited_by_count":9,"area":null},{"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":"2405.19723","title":"Encoding and Controlling Global Semantics for Long-form Video Question Answering","created":"2024-05-30","cited_by_count":8,"area":null},{"id":"2504.07454","title":"How Can Objects Help Video-Language Understanding?","created":"2025-04-10","cited_by_count":8,"area":"mllm"},{"id":"2504.09282","title":"VideoAds for Fast-Paced Video Understanding","created":"2025-04-12","cited_by_count":8,"area":null},{"id":"2505.23922","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2506.06277","title":"ExAct: A Video-Language Benchmark for Expert Action Analysis","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2506.09445","title":"TOGA: Temporally Grounded Open-Ended Video QA with Weak Supervision","created":"2025-06-11","cited_by_count":8,"area":null},{"id":"2506.21742","title":"VRR-QA: Visual Relational Reasoning in Videos Beyond Explicit Cues","created":"2025-06-26","cited_by_count":8,"area":null}],"next_cursor":"100"}