{"total":85,"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":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268,"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":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"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":"2410.13860","title":"VLM-Grounder: A VLM Agent for Zero-Shot 3D Visual Grounding","created":"2024-10-17","cited_by_count":56,"area":null},{"id":"2403.14622","title":"Language Repository for Long Video Understanding","created":"2024-03-21","cited_by_count":55,"area":null},{"id":"2503.06220","title":"StreamMind: Unlocking Full Frame Rate Streaming Video Dialogue through Event-Gated Cognition","created":"2025-03-08","cited_by_count":46,"area":null},{"id":"2409.10917","title":"AMEGO: Active Memory from long EGOcentric videos","created":"2024-09-17","cited_by_count":36,"area":null},{"id":"2512.03627","title":"MemVerse: Multimodal Memory for Lifelong Learning Agents","created":"2025-12-03","cited_by_count":35,"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":"2501.00358","title":"Embodied VideoAgent: Persistent Memory from Egocentric Videos and Embodied Sensors Enables Dynamic Scene Understanding","created":"2024-12-31","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":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"area":null},{"id":"2510.06077","title":"When Thinking Drifts: Evidential Grounding for Robust Video Reasoning","created":"2025-10-07","cited_by_count":16,"area":null},{"id":"2412.01798","title":"SEAL: Semantic Attention Learning for Long Video Representation","created":"2024-12-02","cited_by_count":13,"area":null},{"id":"2501.05037","title":"LongViTU: Instruction Tuning for Long-Form Video Understanding","created":"2025-01-09","cited_by_count":13,"area":null},{"id":"2509.08621","title":"AdsQA: Towards Advertisement Video Understanding","created":"2025-09-10","cited_by_count":13,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2411.16934","title":"Online Episodic Memory Visual Query Localization with Egocentric Streaming Object Memory","created":"2024-11-25","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":"2409.08250","title":"OmniQuery: Contextually Augmenting Captured Multimodal Memory to Enable Personal Question Answering","created":"2024-09-12","cited_by_count":10,"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":"2510.08521","title":"FlowSearch: Advancing deep research with dynamic structured knowledge flow","created":"2025-10-09","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":"2507.02591","title":"AuroraLong: Bringing RNNs Back to Efficient Open-Ended Video Understanding","created":"2025-07-03","cited_by_count":9,"area":null},{"id":"2503.10719","title":"Long-Video Audio Synthesis with Multi-Agent Collaboration","created":"2025-03-13","cited_by_count":8,"area":null},{"id":"2503.09402","title":"VLog: Video-Language Models by Generative Retrieval of Narration Vocabulary","created":"2025-03-12","cited_by_count":7,"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":"2504.19514","title":"FSBench: A Figure Skating Benchmark for Advancing Artistic Sports Understanding","created":"2025-04-28","cited_by_count":6,"area":null},{"id":"2512.13874","title":"SAGE: Training Smart Any-Horizon Agents for Long Video Reasoning with Reinforcement Learning","created":"2025-12-15","cited_by_count":6,"area":null},{"id":"2512.23483","title":"TV-RAG: A Temporal-aware and Semantic Entropy-Weighted Framework for Long Video Retrieval and Understanding","created":"2025-12-29","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":"2503.12855","title":"VITED: Video Temporal Evidence Distillation","created":"2025-03-17","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":"2607.11523","title":"Vinci2: Providing Proactive Assistance in Continuous Egocentric Videos","created":"2026-07-13","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":"2410.23230","title":"Aligning Audio-Visual Joint Representations with an Agentic Workflow","created":"2024-10-30","cited_by_count":4,"area":null},{"id":"2506.04897","title":"From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes","created":"2025-06-05","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":"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":"2607.11487","title":"LightMem-Ego: Your AI Memory for Everyday Life","created":"2026-07-13","cited_by_count":4,"area":null},{"id":"2606.00825","title":"SuperMemory-VQA: An Egocentric Visual Question-Answering Benchmark for Long-Horizon Memory","created":"2026-05-30","cited_by_count":3,"area":null},{"id":"2509.08538","title":"MESH -- Understanding Videos Like Human: Measuring Hallucinations in Large Video Models","created":"2025-09-10","cited_by_count":2,"area":null},{"id":"2509.18754","title":"COLT: Enhancing Video Large Language Models with Continual Tool Usage","created":"2025-09-23","cited_by_count":2,"area":null},{"id":"2602.07625","title":"AD-MIR: Bridging the Gap from Perception to Persuasion in Advertising Video Understanding via Structured Reasoning","created":"2026-02-07","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":"2606.05008","title":"M$^3$Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Tasks","created":"2026-06-03","cited_by_count":2,"area":null},{"id":"2608.03779","title":"AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding","created":"2026-08-04","cited_by_count":2,"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":"2510.15842","title":"Paper2Web: Let's Make Your Paper Alive!","created":"2025-10-17","cited_by_count":1,"area":null},{"id":"2511.17442","title":"REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2603.25645","title":"Colon-Bench: An Agentic Workflow for Scalable Dense Lesion Annotation in Full-Procedure Colonoscopy Videos","created":"2026-03-26","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":"2606.09641","title":"MAVIS: Multi-Agent Video Retrieval via Structured Video Understanding","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.16902","title":"Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models","created":"2026-06-15","cited_by_count":1,"area":null},{"id":"2607.08497","title":"Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing","created":"2026-07-09","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":"2411.17720","title":"MAS-Attention: Memory-Aware Stream Processing for Attention Acceleration on Resource-Constrained Edge Devices","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2507.21589","title":"Exploring the Link Between Bayesian Inference and Embodied Intelligence: Toward Open Physical-World Embodied AI Systems","created":"2025-07-29","cited_by_count":0,"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":"2602.22923","title":"WaterVideoQA: ASV-Centric Perception and Rule-Compliant Reasoning via Multi-Modal Agents","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.12478","title":"Less Data, Faster Convergence: Goal-Driven Data Optimization for Multimodal Instruction Tuning","created":"2026-03-12","cited_by_count":0,"area":null},{"id":"2604.03697","title":"SGTA: Scene-Graph Based Multi-Modal Traffic Agent for Video Understanding","created":"2026-04-04","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":"2604.15622","title":"AdaDINO: Context-Adaptive DINO-Distilled Vision Foundation Models for Efficient Open-Vocabulary Edge Inference","created":"2026-04-17","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":"2607.09759","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":"2607.11798","title":"StoryTeller: Training-Free Narrative Grounding for Long-Form Audio Description","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.28678","title":"ViSAGE: Constructing Self-Correcting Memories for Long-Form Video Understanding","created":"2026-07-29","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":"2609.09895","title":"Can We Trust Video Hallucination Detectors? VidHalLoc for Evaluating the Evaluators","created":"2026-09-09","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":"2609.38155","title":"Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.40195","title":"MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.05526","title":"Have I Scene This Before? Spatially Grounded Conversational Memory for Complex Queries in Egocentric Assistants","created":"2026-10-04","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}],"next_cursor":null}