{"total":113,"rows":[{"id":"2412.14171","title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","created":"2024-12-18","cited_by_count":611,"area":"lr"},{"id":"2501.00574","title":"VideoChat-Flash: Hierarchical Compression for Long-Context Video Modeling","created":"2024-12-31","cited_by_count":220,"area":"mllm"},{"id":"2501.12386","title":"InternVideo2.5: Empowering Video MLLMs with Long and Rich Context Modeling","created":"2025-01-21","cited_by_count":211,"area":"mllm"},{"id":"2502.04326","title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","created":"2025-02-06","cited_by_count":155,"area":"mllm"},{"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":"2506.03135","title":"OmniSpatial: Towards Comprehensive Spatial Reasoning Benchmark for Vision Language Models","created":"2025-06-03","cited_by_count":114,"area":"lr"},{"id":"2501.01428","title":"GPT4Scene: Understand 3D Scenes from Videos with Vision-Language Models","created":"2025-01-02","cited_by_count":109,"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":"2510.08531","title":"SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models","created":"2025-10-09","cited_by_count":90,"area":"lr"},{"id":"2502.01549","title":"VideoRAG: Retrieval-Augmented Generation with Extreme Long-Context Videos","created":"2025-02-03","cited_by_count":77,"area":"rag"},{"id":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68,"area":"mllm"},{"id":"2503.11495","title":"V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning","created":"2025-03-14","cited_by_count":68,"area":"lr"},{"id":"2506.13654","title":"Ego-R1: Chain-of-Tool-Thought for Ultra-Long Egocentric Video Reasoning","created":"2025-06-16","cited_by_count":68,"area":"lr"},{"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":"2512.02425","title":"WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning","created":"2025-12-02","cited_by_count":53,"area":"lr"},{"id":"2502.07411","title":"EgoTextVQA: Towards Egocentric Scene-Text Aware Video Question Answering","created":"2025-02-11","cited_by_count":44,"area":null},{"id":"2503.09146","title":"Generative Frame Sampler for Long Video Understanding","created":"2025-03-12","cited_by_count":37,"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":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2506.09943","title":"CausalVQA: A Physically Grounded Causal Reasoning Benchmark for Video Models","created":"2025-06-11","cited_by_count":35,"area":"lr"},{"id":"2502.12532","title":"CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space","created":"2025-02-18","cited_by_count":32,"area":"agents"},{"id":"2505.00681","title":"MINERVA: Evaluating Complex Video Reasoning","created":"2025-05-01","cited_by_count":32,"area":"lr"},{"id":"2512.05774","title":"Active Video Perception: Iterative Evidence Seeking for Agentic Long Video Understanding","created":"2025-12-05","cited_by_count":29,"area":"agents"},{"id":"2505.11842","title":"Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs","created":"2025-05-17","cited_by_count":28,"area":"mllm"},{"id":"2506.03642","title":"Spatial Understanding from Videos: Structured Prompts Meet Simulation Data","created":"2025-06-04","cited_by_count":28,"area":null},{"id":"2503.24376","title":"Exploring the Effect of Reinforcement Learning on Video Understanding: Insights from SEED-Bench-R1","created":"2025-03-31","cited_by_count":25,"area":"lr"},{"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":"2507.18342","title":"EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs","created":"2025-07-24","cited_by_count":23,"area":null},{"id":"2503.12542","title":"ST-Think: How Multimodal Large Language Models Reason About 4D Worlds from Ego-Centric Videos","created":"2025-03-16","cited_by_count":21,"area":"lr"},{"id":"2505.14640","title":"VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation","created":"2025-05-20","cited_by_count":21,"area":"mllm"},{"id":"2503.12496","title":"Does Your Vision-Language Model Get Lost in the Long Video Sampling Dilemma?","created":"2025-03-16","cited_by_count":20,"area":"mllm"},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2507.09876","title":"ViTCoT: Video-Text Interleaved Chain-of-Thought for Boosting Video Understanding in Large Language Models","created":"2025-07-14","cited_by_count":18,"area":"lr"},{"id":"2506.03922","title":"HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models","created":"2025-06-04","cited_by_count":17,"area":"mllm"},{"id":"2603.20185","title":"VideoSeek: Long-Horizon Video Agent with Tool-Guided Seeking","created":"2026-03-20","cited_by_count":17,"area":"agents"},{"id":"2504.15280","title":"Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs","created":"2025-04-21","cited_by_count":16,"area":"mllm"},{"id":"2504.20091","title":"VideoMultiAgents: A Multi-Agent Framework for Video Question Answering","created":"2025-04-25","cited_by_count":16,"area":"lr"},{"id":"2501.06835","title":"X-LeBench: A Benchmark for Extremely Long Egocentric Video Understanding","created":"2025-01-12","cited_by_count":15,"area":null},{"id":"2512.06866","title":"Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior","created":"2025-12-07","cited_by_count":15,"area":"inference"},{"id":"2509.01907","title":"RSCC: A Large-Scale Remote Sensing Change Caption Dataset for Disaster Events","created":"2025-09-02","cited_by_count":14,"area":null},{"id":"2502.20490","title":"EgoNormia: Benchmarking Physical Social Norm Understanding","created":"2025-02-27","cited_by_count":13,"area":null},{"id":"2506.17873","title":"SurgVidLM: Towards Multi-grained Surgical Video Understanding with Large Language Model","created":"2025-06-22","cited_by_count":13,"area":null},{"id":"2503.19851","title":"Towards Online Multi-Modal Social Interaction Understanding","created":"2025-03-25","cited_by_count":12,"area":null},{"id":"2506.05340","title":"Exploring Diffusion Transformer Designs via Grafting","created":"2025-06-05","cited_by_count":12,"area":"diffusion"},{"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":"2503.18923","title":"Video SimpleQA: Towards Factuality Evaluation in Large Video Language Models","created":"2025-03-24","cited_by_count":11,"area":null},{"id":"2505.22810","title":"VidText: Towards Comprehensive Evaluation for Video Text Understanding","created":"2025-05-28","cited_by_count":11,"area":null},{"id":"2508.00518","title":"Fine-grained Spatiotemporal Grounding on Egocentric Videos","created":"2025-08-01","cited_by_count":11,"area":null},{"id":"2505.24158","title":"Threading Keyframe with Narratives: MLLMs as Strong Long Video Comprehenders","created":"2025-05-30","cited_by_count":10,"area":"mllm"},{"id":"2508.09486","title":"Video-EM: Event-Centric Episodic Memory for Long-Form Video Understanding","created":"2025-08-13","cited_by_count":10,"area":null},{"id":"2503.17827","title":"4D-Bench: Benchmarking Multi-modal Large Language Models for 4D Object Understanding","created":"2025-03-22","cited_by_count":8,"area":"mllm"},{"id":"2505.23922","title":"ScaleLong: A Multi-Timescale Benchmark for Long Video Understanding","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2510.22443","title":"Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents","created":"2025-10-25","cited_by_count":8,"area":"mllm"},{"id":"2602.08439","title":"Demo-ICL: In-Context Learning for Procedural Video Knowledge Acquisition","created":"2026-02-09","cited_by_count":8,"area":"mllm"},{"id":"2503.21699","title":"MAVERIX: Multimodal Audio-Visual Evaluation and Recognition IndeX","created":"2025-03-27","cited_by_count":7,"area":"mllm"},{"id":"2506.14512","title":"SIRI-Bench: Challenging VLMs' Spatial Intelligence through Complex Reasoning Tasks","created":"2025-06-17","cited_by_count":7,"area":"lr"},{"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":"2603.05923","title":"Learning Next Action Predictors from Human-Computer Interaction","created":"2026-03-06","cited_by_count":7,"area":null},{"id":"2501.01645","title":"HLV-1K: A Large-scale Hour-Long Video Benchmark for Time-Specific Long Video Understanding","created":"2025-01-03","cited_by_count":6,"area":"mllm"},{"id":"2506.05523","title":"MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2505.13851","title":"A Challenge to Build Neuro-Symbolic Video Agents","created":"2025-05-20","cited_by_count":5,"area":null},{"id":"2506.06275","title":"Movie Facts and Fibs (MF$^2$): A Benchmark for Long Movie Understanding","created":"2025-06-06","cited_by_count":5,"area":"mllm"},{"id":"2603.00490","title":"LifeEval: A Multimodal Benchmark for Assistive AI in Egocentric Daily Life Tasks","created":"2026-02-28","cited_by_count":5,"area":"mllm"},{"id":"2603.22529","title":"Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos","created":"2026-03-23","cited_by_count":5,"area":"agents"},{"id":"2606.02522","title":"Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events","created":"2026-06-01","cited_by_count":5,"area":"mllm"},{"id":"2605.08271","title":"Bridging Modalities, Spanning Time: Structured Memory for Ultra-Long Agentic Video Reasoning","created":"2026-05-08","cited_by_count":4,"area":"lr"},{"id":"2607.13681","title":"Towards Spatial Supersensing in the Wild","created":"2026-07-15","cited_by_count":4,"area":"wm"},{"id":"2506.13564","title":"State-Space Hierarchical Compression with Gated Attention and Learnable Sampling for Hour-Long Video Understanding in Large Multimodal Models","created":"2025-06-16","cited_by_count":3,"area":"mllm"},{"id":"2507.08104","title":"VideoConviction: A Multimodal Benchmark for Human Conviction and Stock Market Recommendations","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2508.10287","title":"JRDB-Reasoning: A Difficulty-Graded Benchmark for Visual Reasoning in Robotics","created":"2025-08-14","cited_by_count":3,"area":"lr"},{"id":"2509.24563","title":"NeMo: Needle in a Montage for Video-Language Understanding","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2603.04349","title":"FocusGraph: Graph-Structured Frame Selection for Embodied Long Video Question Answering","created":"2026-03-04","cited_by_count":3,"area":null},{"id":"2605.10936","title":"Personal Visual Context Learning in Large Multimodal Models","created":"2026-05-11","cited_by_count":3,"area":"mllm"},{"id":"2605.30346","title":"YoCausal: How Far is Video Generation from World Model? A Causality Perspective","created":"2026-05-28","cited_by_count":3,"area":"wm"},{"id":"2607.02607","title":"Latent Visual Cache for Video Reasoning","created":"2026-07-01","cited_by_count":3,"area":"mllm"},{"id":"2608.13113","title":"EgoMonth: A Month-Level Egocentric Video Benchmark for Long-Term Spatiotemporal Memory","created":"2026-08-13","cited_by_count":3,"area":"mllm"},{"id":"2508.13692","title":"HumanPCR: Probing MLLM Capabilities in Diverse Human-Centric Scenes","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2510.21160","title":"Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2601.06309","title":"VideoWeave: A Data-Centric Approach for Efficient Video Understanding","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2606.05008","title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2607.02959","title":"Incentivizing Vision Language Models to Search for Long Video Question Answering","created":"2026-07-03","cited_by_count":2,"area":"mllm"},{"id":"2505.12605","title":"Temporal-Oriented Recipe for Transferring Large Vision-Language Model to Video Understanding","created":"2025-05-19","cited_by_count":1,"area":"mllm"},{"id":"2511.17914","title":"Rectifying Soft-Label Entangled Bias in Long-Tailed Dataset Distillation","created":"2025-11-22","cited_by_count":1,"area":null},{"id":"2605.15342","title":"Minerva-Ego: Spatiotemporal Hints for Egocentric Video Understanding","created":"2026-05-14","cited_by_count":1,"area":"lr"},{"id":"2606.03920","title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.15320","title":"Conditional Multi-Event Temporal Grounding in Long-Form Video","created":"2026-06-13","cited_by_count":1,"area":"mllm"},{"id":"2607.01784","title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","created":"2026-07-02","cited_by_count":1,"area":"lr"},{"id":"2608.00714","title":"Coverage-Driven Adaptive Keyframe Selection for Video Understanding","created":"2026-08-01","cited_by_count":1,"area":"mllm"},{"id":"2608.21430","title":"Evaluating Multimodal Narrative Understanding of Popular Hollywood Films","created":"2026-08-17","cited_by_count":1,"area":"mllm"},{"id":"2503.19850","title":"FALCONEye: Finding Answers and Localizing Content in ONE-hour-long videos with multi-modal LLMs","created":"2025-03-25","cited_by_count":0,"area":"mllm"},{"id":"2509.19002","title":"VIR-Bench: Evaluating Geospatial and Temporal Understanding of MLLMs via Travel Video Itinerary Reconstruction","created":"2025-09-23","cited_by_count":0,"area":"mllm"},{"id":"2510.21679","title":"A Multimodal Benchmark for Framing of Oil & Gas Advertising and Potential Greenwashing Detection","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2602.09255","title":"STaR: Scalable Task-Conditioned Retrieval for Long-Horizon Multimodal Robot Memory","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.27259","title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2604.08342","title":"EgoEverything: A Benchmark for Human Behavior Inspired Long Context Egocentric Video Understanding in AR Environment","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2604.26565","title":"DenseStep2M: A Scalable, Training-Free Pipeline for Dense Instructional Video Annotation","created":"2026-04-29","cited_by_count":0,"area":null},{"id":"2605.06185","title":"Event-Causal RAG: A Retrieval-Augmented Generation Framework for Long Video Reasoning in Complex Scenarios","created":"2026-05-07","cited_by_count":0,"area":"lr"},{"id":"2605.11462","title":"SpatialForge: Bootstrapping 3D-Aware Spatial Reasoning from Open-World 2D Images","created":"2026-05-12","cited_by_count":0,"area":"lr"},{"id":"2605.19223","title":"HAVEN: Hierarchically Aligned Multimodal Benchmark for Unified Video Understanding","created":"2026-05-19","cited_by_count":0,"area":"mllm"}],"next_cursor":"100"}