{"total":110,"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":"2501.13106","title":"VideoLLaMA 3: Frontier Multimodal Foundation Models for Image and Video Understanding","created":"2025-01-22","cited_by_count":518,"area":null},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2406.08085","title":"Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams","created":"2024-06-12","cited_by_count":169,"area":null},{"id":"2405.16009","title":"Streaming Long Video Understanding with Large Language Models","created":"2024-05-25","cited_by_count":167,"area":null},{"id":"2409.12961","title":"Oryx MLLM: On-Demand Spatial-Temporal Understanding at Arbitrary Resolution","created":"2024-09-19","cited_by_count":159,"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":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"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":"2411.04998","title":"HourVideo: 1-Hour Video-Language Understanding","created":"2024-11-07","cited_by_count":113,"area":null},{"id":"2410.03290","title":"Grounded-VideoLLM: Sharpening Fine-grained Temporal Grounding in Video Large Language Models","created":"2024-10-04","cited_by_count":91,"area":null},{"id":"2406.18522","title":"ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation","created":"2024-06-26","cited_by_count":75,"area":null},{"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":"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":"2501.15111","title":"HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding","created":"2025-01-25","cited_by_count":60,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2407.03104","title":"KeyVideoLLM: Towards Large-scale Video Keyframe Selection","created":"2024-07-03","cited_by_count":54,"area":null},{"id":"2503.11187","title":"FastVID: Dynamic Density Pruning for Fast Video Large Language Models","created":"2025-03-14","cited_by_count":52,"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":"2410.07752","title":"Lost in Time: A New Temporal Benchmark for VideoLLMs","created":"2024-10-10","cited_by_count":42,"area":null},{"id":"2504.14693","title":"Video-MMLU: A Massive Multi-Discipline Lecture Understanding Benchmark","created":"2025-04-20","cited_by_count":37,"area":null},{"id":"2502.12081","title":"Unhackable Temporal Rewarding for Scalable Video MLLMs","created":"2025-02-17","cited_by_count":33,"area":null},{"id":"2503.18943","title":"SlowFast-LLaVA-1.5: A Family of Token-Efficient Video Large Language Models for Long-Form Video Understanding","created":"2025-03-24","cited_by_count":30,"area":null},{"id":"2507.13353","title":"VideoITG: Multimodal Video Understanding with Instructed Temporal Grounding","created":"2025-07-17","cited_by_count":29,"area":null},{"id":"2503.23715","title":"HOIGen-1M: A Large-scale Dataset for Human-Object Interaction Video Generation","created":"2025-03-31","cited_by_count":26,"area":null},{"id":"2505.19650","title":"Modality Curation: Building Universal Embeddings for Advanced Multimodal Information Retrieval","created":"2025-05-26","cited_by_count":26,"area":null},{"id":"2410.10816","title":"LVD-2M: A Long-take Video Dataset with Temporally Dense Captions","created":"2024-10-14","cited_by_count":25,"area":null},{"id":"2511.05299","title":"LiveStar: Live Streaming Assistant for Real-World Online Video Understanding","created":"2025-11-07","cited_by_count":25,"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":"2409.01071","title":"VideoLLaMB: Long Streaming Video Understanding with Recurrent Memory Bridges","created":"2024-09-02","cited_by_count":20,"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":"2502.11664","title":"VRoPE: Rotary Position Embedding for Video Large Language Models","created":"2025-02-17","cited_by_count":18,"area":null},{"id":"2410.10441","title":"Free Video-LLM: Prompt-guided Visual Perception for Efficient Training-free Video LLMs","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2409.06299","title":"Enhancing Long Video Understanding via Hierarchical Event-Based Memory","created":"2024-09-10","cited_by_count":14,"area":null},{"id":"2412.13845","title":"Do Language Models Understand Time?","created":"2024-12-18","cited_by_count":14,"area":null},{"id":"2503.13016","title":"Efficient Motion-Aware Video MLLM","created":"2025-03-17","cited_by_count":14,"area":null},{"id":"2509.22820","title":"MMPB: It's Time for Multi-Modal Personalization","created":"2025-09-26","cited_by_count":14,"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":"2503.17069","title":"PVChat: Personalized Video Chat with One-Shot Learning","created":"2025-03-21","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":"2509.11866","title":"Dr.V: A Hierarchical Perception-Temporal-Cognition Framework to Diagnose Video Hallucination by Fine-grained Spatial-Temporal Grounding","created":"2025-09-15","cited_by_count":13,"area":null},{"id":"2605.18678","title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","created":"2026-05-18","cited_by_count":12,"area":null},{"id":"2409.04388","title":"Question-Answering Dense Video Events","created":"2024-09-06","cited_by_count":11,"area":null},{"id":"2412.02071","title":"Progress-Aware Video Frame Captioning","created":"2024-12-03","cited_by_count":11,"area":null},{"id":"2602.13191","title":"CoPE-VideoLM: Leveraging Codec Primitives For Efficient Video Language Modeling","created":"2026-02-13","cited_by_count":11,"area":null},{"id":"2411.12355","title":"DynFocus: Dynamic Cooperative Network Empowers LLMs with Video Understanding","created":"2024-11-19","cited_by_count":10,"area":null},{"id":"2502.11594","title":"iMOVE: Instance-Motion-Aware Video Understanding","created":"2025-02-17","cited_by_count":10,"area":null},{"id":"2602.16110","title":"OmniCT: Towards a Unified Slice-Volume LVLM for Comprehensive CT Analysis","created":"2026-02-18","cited_by_count":10,"area":null},{"id":"2410.07151","title":"DH-FaceVid-1K: A Large-Scale High-Quality Dataset for Face Video Generation","created":"2024-09-23","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":"2505.20124","title":"TUNA: Comprehensive Fine-grained Temporal Understanding Evaluation on Dense Dynamic Videos","created":"2025-05-26","cited_by_count":9,"area":null},{"id":"2505.23484","title":"VCapsBench: A Large-scale Fine-grained Benchmark for Video Caption Quality Evaluation","created":"2025-05-29","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":"2510.02778","title":"AdaRD-key: Adaptive Relevance-Diversity Keyframe Sampling for Long-form Video understanding","created":"2025-10-03","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":"2503.18422","title":"Breaking the Encoder Barrier for Seamless Video-Language Understanding","created":"2025-03-24","cited_by_count":8,"area":null},{"id":"2510.24134","title":"VC4VG: Optimizing Video Captions for Text-to-Video Generation","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2407.18908","title":"Wolf: Dense Video Captioning with a World Summarization Framework","created":"2024-07-26","cited_by_count":7,"area":null},{"id":"2505.24329","title":"DisTime: Distribution-based Time Representation for Video Large Language Models","created":"2025-05-30","cited_by_count":7,"area":null},{"id":"2406.14877","title":"Sports Intelligence: Assessing the Sports Understanding Capabilities of Language Models through Question Answering from Text to Video","created":"2024-06-21","cited_by_count":6,"area":null},{"id":"2409.19532","title":"Video DataFlywheel: Resolving the Impossible Data Trinity in Video-Language Understanding","created":"2024-09-29","cited_by_count":6,"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":"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":"2408.09333","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","created":"2024-08-18","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":"2504.07594","title":"Extending Visual Dynamics for Video-to-Music Generation","created":"2025-04-10","cited_by_count":4,"area":null},{"id":"2505.20920","title":"HuMoCon: Concept Discovery for Human Motion Understanding","created":"2025-05-27","cited_by_count":4,"area":null},{"id":"2512.24097","title":"Factorized Learning for Temporally Grounded Video-Language Models","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2601.12193","title":"VeRVE: Versatile Retrieval for Videos via Unified Embeddings","created":"2026-01-17","cited_by_count":4,"area":null},{"id":"2411.16804","title":"InTraGen: Trajectory-controlled Video Generation for Object Interactions","created":"2024-11-25","cited_by_count":3,"area":null},{"id":"2503.09081","title":"Everything Can Be Described in Words: A Simple Unified Multi-Modal Framework with Semantic and Temporal Alignment","created":"2025-03-12","cited_by_count":3,"area":null},{"id":"2504.03501","title":"LV-MAE: Learning Long Video Representations through Masked-Embedding Autoencoders","created":"2025-04-04","cited_by_count":3,"area":null},{"id":"2506.07811","title":"Looking Beyond Visible Cues: Implicit Video Question Answering via Dual-Clue Reasoning","created":"2025-06-09","cited_by_count":3,"area":null},{"id":"2508.06511","title":"DiTalker: A Unified DiT-based Framework for High-Quality and Speaking Styles Controllable Portrait Animation","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2405.20684","title":"Joint Embeddings for Graph Instruction Tuning","created":"2024-05-31","cited_by_count":2,"area":null},{"id":"2411.16199","title":"VIRES: Video Instance Repainting via Sketch and Text Guided Generation","created":"2024-11-25","cited_by_count":2,"area":null},{"id":"2503.09027","title":"Measure Twice, Cut Once: A Semantic-Oriented Approach to Video Temporal Localization with Video LLMs","created":"2025-03-12","cited_by_count":2,"area":null},{"id":"2503.09279","title":"Cockatiel: Ensembling Synthetic and Human Preferenced Training for Detailed Video Caption","created":"2025-03-12","cited_by_count":2,"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":"2508.21094","title":"EMCompress: Video-LLMs with Endomorphic Multimodal Compression","created":"2025-08-27","cited_by_count":2,"area":null},{"id":"2601.17868","title":"VidLaDA: Bidirectional Diffusion Large Language Models for Efficient Video Understanding","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2601.20742","title":"Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unification","created":"2026-01-28","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":"2606.13289","title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2606.31933","title":"No Place to Hide: Benchmarking Video Hallucination with Background-Controlled Pairs","created":"2026-06-30","cited_by_count":2,"area":null},{"id":"2601.02908","title":"TA-Prompting: Enhancing Video Large Language Models for Dense Video Captioning via Temporal Anchors","created":"2026-01-06","cited_by_count":1,"area":null},{"id":"2601.07366","title":"HiVid-Narrator: Hierarchical Video Narrative Generation with Scene-Primed ASR-anchored Compression","created":"2026-01-12","cited_by_count":1,"area":null},{"id":"2601.14594","title":"LFS: Learnable Frame Selector for Event-Aware and Temporally Diverse Video Captioning","created":"2026-01-21","cited_by_count":1,"area":null},{"id":"2601.16471","title":"Order from Chaos: Physical World Understanding from Glitchy Gameplay Videos","created":"2026-01-23","cited_by_count":1,"area":null},{"id":"2602.05215","title":"E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching","created":"2026-02-05","cited_by_count":1,"area":null},{"id":"2604.03045","title":"STEAR: Layer-Aware Spatiotemporal Evidence Intervention for Hallucination Mitigation in Video Large Language Models","created":"2026-04-03","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":"2606.06991","title":"Don't Pause: Streaming Video-Language Synchrony for Online Video Understanding","created":"2026-06-05","cited_by_count":1,"area":null},{"id":"2607.05090","title":"Be Indiscrete: The Benefits of Learning Continuous Spine Degeneration Severity Scores","created":"2026-07-06","cited_by_count":1,"area":null},{"id":"2609.05141","title":"SciDocBench: A Workflow-Centered Benchmark and Data Pipeline for Scientific Document Understanding","created":"2026-09-04","cited_by_count":1,"area":null},{"id":"2508.04549","title":"MSC: A Marine Wildlife Video Dataset with Grounded Segmentation and Clip-Level Captioning","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2510.03955","title":"Harnessing Synthetic Preference Data for Enhancing Temporal Understanding of Video-LLMs","created":"2025-10-04","cited_by_count":0,"area":null}],"next_cursor":"100"}