{"total":96,"rows":[{"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":"2407.00634","title":"Tarsier: Recipes for Training and Evaluating Large Video Description Models","created":"2024-06-30","cited_by_count":141,"area":null},{"id":"2501.03218","title":"Dispider: Enabling Video LLMs with Active Real-Time Interaction via Disentangled Perception, Decision, and Reaction","created":"2025-01-06","cited_by_count":127,"area":null},{"id":"2407.15841","title":"SlowFast-LLaVA: A Strong Training-Free Baseline for Video Large Language Models","created":"2024-07-22","cited_by_count":125,"area":null},{"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":"2406.09396","title":"Too Many Frames, Not All Useful: Efficient Strategies for Long-Form Video QA","created":"2024-06-13","cited_by_count":68,"area":null},{"id":"2406.12846","title":"DrVideo: Document Retrieval Based Long Video Understanding","created":"2024-06-18","cited_by_count":65,"area":null},{"id":"2502.05173","title":"VideoRoPE: What Makes for Good Video Rotary Position Embedding?","created":"2025-02-07","cited_by_count":65,"area":null},{"id":"2501.02885","title":"MDP3: A Training-free Approach for List-wise Frame Selection in Video-LLMs","created":"2025-01-06","cited_by_count":43,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2503.13139","title":"Logic-in-Frames: Dynamic Keyframe Search via Visual Semantic-Logical Verification for Long Video Understanding","created":"2025-03-17","cited_by_count":34,"area":null},{"id":"2408.04223","title":"VideoQA in the Era of LLMs: An Empirical Study","created":"2024-08-08","cited_by_count":29,"area":null},{"id":"2506.10821","title":"VideoExplorer: Think With Videos For Agentic Long-Video Understanding","created":"2025-06-12","cited_by_count":29,"area":null},{"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":"2603.19217","title":"LVOmniBench: Pioneering Long Audio-Video Understanding Evaluation for Omnimodal LLMs","created":"2026-03-19","cited_by_count":24,"area":null},{"id":"2504.16082","title":"MR. Video: \"MapReduce\" is the Principle for Long Video Understanding","created":"2025-04-22","cited_by_count":23,"area":null},{"id":"2510.12422","title":"VideoLucy: Deep Memory Backtracking for Long Video Understanding","created":"2025-10-14","cited_by_count":22,"area":null},{"id":"2603.08620","title":"StreamReady: Learning What to Answer and When in Long Streaming Videos","created":"2026-03-09","cited_by_count":19,"area":null},{"id":"2502.03183","title":"MaxInfo: A Training-Free Key-Frame Selection Method Using Maximum Volume for Enhanced Video Understanding","created":"2025-02-05","cited_by_count":18,"area":null},{"id":"2510.22693","title":"VADTree: Explainable Training-Free Video Anomaly Detection via Hierarchical Granularity-Aware Tree","created":"2025-10-26","cited_by_count":18,"area":null},{"id":"2412.09601","title":"TimeRefine: Temporal Grounding with Time Refining Video LLM","created":"2024-12-12","cited_by_count":15,"area":null},{"id":"2501.19098","title":"$\\infty$-Video: A Training-Free Approach to Long Video Understanding via Continuous-Time Memory Consolidation","created":"2025-01-31","cited_by_count":14,"area":null},{"id":"2504.01407","title":"ZoomV: Temporal Zoom-in for Efficient Long Video Understanding","created":"2025-04-02","cited_by_count":10,"area":null},{"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":"2504.00072","title":"Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2504.07519","title":"VideoExpert: Augmented LLM for Temporal-Sensitive Video Understanding","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2506.06144","title":"CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval","created":"2025-06-06","cited_by_count":9,"area":null},{"id":"2510.05836","title":"Flow4Agent: Long-form Video Understanding via Motion Prior from Optical Flow","created":"2025-10-07","cited_by_count":9,"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":"2602.20913","title":"LongVideo-R1: Smart Navigation for Low-cost Long Video Understanding","created":"2026-02-24","cited_by_count":7,"area":null},{"id":"2504.06835","title":"LVC: A Lightweight Compression Framework for Enhancing VLMs in Long Video Understanding","created":"2025-04-09","cited_by_count":6,"area":null},{"id":"2501.14194","title":"ENTER: Event Based Interpretable Reasoning for VideoQA","created":"2025-01-24","cited_by_count":5,"area":null},{"id":"2504.17213","title":"MASR: Self-Reflective Reasoning through Multimodal Hierarchical Attention Focusing for Agent-based Video Understanding","created":"2025-04-24","cited_by_count":5,"area":null},{"id":"2507.00033","title":"Moment Sampling in Video LLMs for Long-Form Video QA","created":"2025-06-18","cited_by_count":5,"area":null},{"id":"2604.18459","title":"Progressive Online Video Understanding with Evidence-Aligned Timing and Transparent Decisions","created":"2026-04-20","cited_by_count":5,"area":null},{"id":"2409.17702","title":"Episodic Memory Verbalization using Hierarchical Representations of Life-Long Robot Experience","created":"2024-09-26","cited_by_count":4,"area":null},{"id":"2504.05925","title":"SVLTA: Benchmarking Vision-Language Temporal Alignment via Synthetic Video Situation","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2506.00891","title":"Uneven Event Modeling for Partially Relevant Video Retrieval","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2507.14784","title":"LeAdQA: LLM-Driven Context-Aware Temporal Grounding for Video Question Answering","created":"2025-07-20","cited_by_count":4,"area":null},{"id":"2509.20851","title":"Poisoning Prompt-Guided Sampling in Video Large Language Models","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2603.14935","title":"Video-CoE: Reinforcing Video Event Prediction via Chain of Events","created":"2026-03-16","cited_by_count":4,"area":null},{"id":"2604.05079","title":"SVAgent: Storyline-Guided Long Video Understanding via Cross-Modal Multi-Agent Collaboration","created":"2026-04-06","cited_by_count":4,"area":null},{"id":"2606.19341","title":"Native Active Perception as Reasoning for Omni-Modal Understanding","created":"2026-06-17","cited_by_count":4,"area":null},{"id":"2607.13298","title":"FOLIO: Focused Semantic Memory for Streaming Video Understanding","created":"2026-07-14","cited_by_count":4,"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":"2608.04587","title":"MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2503.11205","title":"LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2507.09068","title":"Infinite Video Understanding","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2508.21094","title":"EMCompress: Video-LLMs with Endomorphic Multimodal Compression","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2509.08016","title":"Video Parallel Scaling: Aggregating Diverse Frame Subsets for VideoLLMs","created":"2025-09-09","cited_by_count":2,"area":null},{"id":"2604.02891","title":"Progressive Video Condensation with MLLM Agent for Long-form Video Understanding","created":"2026-04-03","cited_by_count":2,"area":null},{"id":"2606.27922","title":"Reflect-R1: Evidence-Driven Reflection for Self-Correction in Long Video Understanding","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2608.20805","title":"Routing Before Looking: Query-Adaptive Evidence Acquisition for Long-form Video Understanding","created":"2026-08-21","cited_by_count":2,"area":null},{"id":"2608.22516","title":"TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video Understanding","created":"2026-08-23","cited_by_count":2,"area":null},{"id":"2505.01578","title":"Grounding Task Assistance with Multimodal Cues from a Single Demonstration","created":"2025-05-02","cited_by_count":1,"area":null},{"id":"2506.21891","title":"DIVE: Deep-search Iterative Video Exploration A Technical Report for the CVRR Challenge at CVPR 2025","created":"2025-06-27","cited_by_count":1,"area":null},{"id":"2508.17932","title":"See What You Need: Query-Aware Visual Intelligence through Reasoning-Perception Loops","created":"2025-08-25","cited_by_count":1,"area":null},{"id":"2508.19024","title":"ProPy: Building Interactive Prompt Pyramids upon CLIP for Partially Relevant Video Retrieval","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2509.23433","title":"SPIKE-RL: Video-LLMs meet Bayesian Surprise","created":"2025-09-27","cited_by_count":1,"area":null},{"id":"2512.11534","title":"HFS: Holistic Query-Aware Frame Selection for Efficient Video Understanding","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2603.17948","title":"VideoAtlas: Navigating Long-Form Video in Logarithmic Compute","created":"2026-03-18","cited_by_count":1,"area":null},{"id":"2603.20180","title":"Adaptive Greedy Frame Selection for Long Video Understanding","created":"2026-03-20","cited_by_count":1,"area":null},{"id":"2604.21444","title":"HiCrew: Hierarchical Reasoning for Long-Form Video Understanding via Question-Aware Multi-Agent Collaboration","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2605.09223","title":"CREST: Curvature-Regulated Event-Centric Sampling for Efficient Long-Video Understanding","created":"2026-05-09","cited_by_count":1,"area":null},{"id":"2605.19075","title":"CRAFT: Critic-Refined Adaptive Key-Frame Targeting for Multimodal Video Question Answering","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.23826","title":"Decomposing Queries into Tool Calls for Long-Video Keyframe Retrieval","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2607.00446","title":"VideoSearch-R1: Iterative Video Retrieval and Reasoning via Soft Query Refinement","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.26355","title":"Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long Videos","created":"2026-08-26","cited_by_count":1,"area":null},{"id":"2609.00551","title":"EM^2Mem: Event-Centric Multimodal Memory for Large Language Models","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2609.12517","title":"One Skill Does Not Fit All: Automatic Discovery and Taxonomy-Guided Routing of Frame-Selection Skills for Long-Video Question Answering","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2508.03039","title":"VideoForest: Person-Anchored Hierarchical Reasoning for Cross-Video Question Answering","created":"2025-08-05","cited_by_count":0,"area":null},{"id":"2601.21802","title":"A Unified XAI-LLM Approach for EndotrachealSuctioning Activity Recognition","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2603.07559","title":"Active Inference for Micro-Gesture Recognition: EFE-Guided Temporal Sampling and Adaptive Learning","created":"2026-03-08","cited_by_count":0,"area":null},{"id":"2604.11004","title":"Panoptic Pairwise Distortion Graph","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.01512","title":"Two-Pass Zero-Shot Temporal-Spatial Grounding of Rare Traffic Events in Surveillance Video","created":"2026-05-02","cited_by_count":0,"area":null},{"id":"2606.06338","title":"StoryVideoQA: Scaling Deep Video Understanding with a Large-Scale, Multi-Genre and Auto-Generated Dataset","created":"2026-06-04","cited_by_count":0,"area":null},{"id":"2606.06532","title":"GOPAgen: Codec-Aware Agentic Long-Video Understanding with Structured Memory","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.11913","title":"From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2607.00867","title":"EFlow: Learning Evidence Flow for Long-Video Reasoning with Adaptive Reflection","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.09759","title":"ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.15778","title":"Modularized Dynamic-Granularity Video LLM for Multi-Event Long Video Understanding","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.00232","title":"Real-Time Visual Obstruction Detection in Surgical Augmented Reality","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.07585","title":"LAVE: Latent Visual Evidence-Enhanced Planning for Video Tool-use Agents","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.15685","title":"Counterfactual Sensitivity Is Not Repairability: Auditing Replay Probes for Video Evidence","created":"2026-08-16","cited_by_count":0,"area":null},{"id":"2608.22975","title":"Budget-Constrained Embodied Perception: Four Resource Walls and a Pre-Registered Evaluation of Access-Structured Perception on Open Models at less than 31B","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.27929","title":"Training-Free Temporal Abstraction for General Video Understanding","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.31005","title":"From Intent to Evidence: Policy-Steered Multi-Strategy Retrieval for Long-Video Agents","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.19610","title":"SIMLIFE: Pattern Understanding for Long-Horizon Human-Agent Partnership","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.19664","title":"VideoResearcher: Self-Improving Tool Design for Long-Video Understanding","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.36875","title":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.03099","title":"Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video Reasoning","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.13915","title":"Where to Look Matters: Rethinking Sub-Volume Sampling in 3D Medical Self-supervised Learning","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.15389","title":"VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.15915","title":"VIEWCRAFT: Evolving What Multimodal Agents See and How They Read It","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}