{"total":81,"rows":[{"id":"2506.09985","title":"V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning","created":"2025-06-11","cited_by_count":809,"area":"wm"},{"id":"2506.09113","title":"Seedance 1.0: Exploring the Boundaries of Video Generation Models","created":"2025-06-10","cited_by_count":259,"area":"diffusion"},{"id":"2504.17343","title":"TimeChat-Online: 80% Visual Tokens are Naturally Redundant in Streaming Videos","created":"2025-04-24","cited_by_count":97,"area":null},{"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":"2512.04040","title":"RELIC: Interactive Video World Model with Long-Horizon Memory","created":"2025-12-03","cited_by_count":96,"area":"wm"},{"id":"2510.22200","title":"LongCat-Video Technical Report","created":"2025-10-25","cited_by_count":85,"area":"wm"},{"id":"2509.01563","title":"Kwai Keye-VL 1.5 Technical Report","created":"2025-09-01","cited_by_count":73,"area":"mllm"},{"id":"2502.04896","title":"Goku: Flow Based Video Generative Foundation Models","created":"2025-02-07","cited_by_count":67,"area":"diffusion"},{"id":"2504.15376","title":"Towards Understanding Camera Motions in Any Video","created":"2025-04-21","cited_by_count":64,"area":null},{"id":"2508.15761","title":"Waver: Wave Your Way to Lifelike Video Generation","created":"2025-08-21","cited_by_count":52,"area":null},{"id":"2507.01949","title":"Kwai Keye-VL Technical Report","created":"2025-07-02","cited_by_count":47,"area":"mllm"},{"id":"2511.04675","title":"InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation","created":"2025-11-06","cited_by_count":45,"area":null},{"id":"2605.25979","title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","created":"2026-05-25","cited_by_count":39,"area":"mllm"},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35,"area":null},{"id":"2506.01725","title":"VideoCap-R1: Enhancing MLLMs for Video Captioning via Structured Thinking","created":"2025-06-02","cited_by_count":30,"area":"lr"},{"id":"2510.10395","title":"AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration","created":"2025-10-12","cited_by_count":27,"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":"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":"2512.06810","title":"MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning","created":"2025-12-07","cited_by_count":22,"area":"mllm"},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2509.01085","title":"Bidirectional Sparse Attention for Faster Video Diffusion Training","created":"2025-09-01","cited_by_count":19,"area":"diffusion"},{"id":"2512.12772","title":"JointAVBench: A Benchmark for Joint Audio-Visual Reasoning Evaluation","created":"2025-12-14","cited_by_count":17,"area":"lr"},{"id":"2508.15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","created":"2025-08-21","cited_by_count":16,"area":null},{"id":"2603.12938","title":"Thinking in Streaming Video","created":"2026-03-13","cited_by_count":16,"area":null},{"id":"2506.09079","title":"VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks","created":"2025-06-10","cited_by_count":14,"area":"mllm"},{"id":"2601.19267","title":"DiaDem: Advancing Dialogue Descriptions in Audiovisual Video Captioning for Multimodal Large Language Models","created":"2026-01-27","cited_by_count":13,"area":"mllm"},{"id":"2508.18634","title":"OwlCap: Harmonizing Motion-Detail for Video Captioning via HMD-270K and Caption Set Equivalence Reward","created":"2025-08-26","cited_by_count":12,"area":null},{"id":"2603.13615","title":"Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis","created":"2026-03-13","cited_by_count":12,"area":"wm"},{"id":"2506.01674","title":"MotionSight: Boosting Fine-Grained Motion Understanding in Multimodal LLMs","created":"2025-06-02","cited_by_count":11,"area":"mllm"},{"id":"2509.24427","title":"UI2V-Bench: An Understanding-based Image-to-video Generation Benchmark","created":"2025-09-29","cited_by_count":11,"area":"diffusion"},{"id":"2602.08711","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2607.14935","title":"VideoChat3: Fully Open Video MLLM for Efficient and Generalist Video Understanding","created":"2026-07-16","cited_by_count":10,"area":null},{"id":"2601.17756","title":"MV-S2V: Multi-View Subject-Consistent Video Generation","created":"2026-01-25","cited_by_count":9,"area":null},{"id":"2601.22301","title":"Coarse-to-Real: Generative Rendering for Populated Dynamic Scenes","created":"2026-01-29","cited_by_count":9,"area":null},{"id":"2602.13013","title":"Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions","created":"2026-02-13","cited_by_count":9,"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},{"id":"2606.09393","title":"CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning","created":"2026-06-08","cited_by_count":8,"area":"mllm"},{"id":"2510.18726","title":"IF-VidCap: Can Video Caption Models Follow Instructions?","created":"2025-10-21","cited_by_count":7,"area":"mllm"},{"id":"2508.04197","title":"Gather and Trace: Rethinking Video TextVQA from an Instance-oriented Perspective","created":"2025-08-06","cited_by_count":5,"area":"lr"},{"id":"2512.19020","title":"CETCAM: Camera-Controllable Video Generation via Consistent and Extensible Tokenization","created":"2025-12-22","cited_by_count":5,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2606.07433","title":"Watch, Remember, Reason: Human-View Video Understanding with MLLMs","created":"2026-06-05","cited_by_count":4,"area":"lr"},{"id":"2503.16929","title":"TEMPLE: Incentivizing Temporal Understanding of Video Large Language Models via Progressive Pre-SFT Alignment","created":"2025-03-21","cited_by_count":3,"area":"alignment"},{"id":"2507.20783","title":"On The Role of Pretrained Language Models in General-Purpose Text Embeddings: A Survey","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2509.24563","title":"NeMo: Needle in a Montage for Video-Language Understanding","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2603.13119","title":"Geometry-Guided Camera Motion Understanding in VideoLLMs","created":"2026-03-13","cited_by_count":3,"area":"mllm"},{"id":"2607.01667","title":"Temporal and Cross-Modal Alignment for Enhanced Audiovisual Video Captioning","created":"2026-07-02","cited_by_count":3,"area":"mllm"},{"id":"2607.05150","title":"Claim-Level Rubric Rewards for Video Caption Reinforcement Learning","created":"2026-07-06","cited_by_count":3,"area":"alignment"},{"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":"2505.22396","title":"Zooming from Context to Cue: Hierarchical Preference Optimization for Multi-Image MLLMs","created":"2025-05-28","cited_by_count":2,"area":"mllm"},{"id":"2512.02457","title":"Does Hearing Help Seeing? Investigating Audio-Video Joint Denoising for Video Generation","created":"2025-12-02","cited_by_count":2,"area":null},{"id":"2512.07136","title":"A Large-Scale Multimodal Dataset and Benchmarks for Human Activity Scene Understanding and Reasoning","created":"2025-12-08","cited_by_count":2,"area":"lr"},{"id":"2602.17768","title":"KPM-Bench: A Kinematic Parsing Motion Benchmark for Fine-grained Motion-centric Video Understanding","created":"2026-02-19","cited_by_count":2,"area":null},{"id":"2603.10652","title":"Are Video Reasoning Models Ready to Go Outside?","created":"2026-03-11","cited_by_count":2,"area":"lr"},{"id":"2603.17651","title":"Anchoring and Rescaling Attention for Semantically Coherent Inbetweening","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2606.21949","title":"CapRiCorn-1K: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales","created":"2026-06-20","cited_by_count":2,"area":null},{"id":"2606.24636","title":"CineCap: Structured Reasoning with Spatio-Temporal Anchors for Cinematographic Video Captioning","created":"2026-06-23","cited_by_count":2,"area":"lr"},{"id":"2608.16320","title":"StreamOPD: A Post-Training Recipe with Spatio-Temporal Cue Gating for Streaming Video Understanding","created":"2026-08-17","cited_by_count":2,"area":"distill"},{"id":"2505.01743","title":"An LLM-Empowered Low-Resolution Vision System for On-Device Human Behavior Understanding","created":"2025-05-03","cited_by_count":1,"area":"mllm"},{"id":"2506.02845","title":"Go Beyond Earth: Understanding Human Actions and Scenes in Microgravity Environments","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2506.06928","title":"How Important are Videos for Training Video LLMs?","created":"2025-06-07","cited_by_count":1,"area":"lr"},{"id":"2512.13677","title":"JoVA: Unified Multimodal Learning for Joint Video-Audio Generation and Editing","created":"2025-12-15","cited_by_count":1,"area":null},{"id":"2602.02341","title":"LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization","created":"2026-02-02","cited_by_count":1,"area":"lr"},{"id":"2605.28023","title":"VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2605.31075","title":"Task-Focused Memorization for Multimodal Agents","created":"2026-05-29","cited_by_count":1,"area":"agents"},{"id":"2606.29531","title":"MotionAtlas: Detailed Region Captioning for Motion-Centric Videos","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.01117","title":"MoHallBench: A Benchmark for Motion Hallucination in Video Large Language Models","created":"2026-07-01","cited_by_count":1,"area":null},{"id":"2608.27881","title":"StreamEMS: Streaming Video Understanding with Self-Evolving Memory Scheme for Vision-Language Models","created":"2026-08-28","cited_by_count":1,"area":"mllm"},{"id":"2609.35507","title":"ReVA: A Scene-Centric Dataset Beyond Repetition for Remote Sensing Video Question Answering","created":"2026-09-28","cited_by_count":1,"area":"mllm"},{"id":"2511.20563","title":"A Reason-then-Describe Instruction Interpreter for Controllable Video Generation","created":"2025-11-25","cited_by_count":0,"area":"diffusion"},{"id":"2512.13511","title":"Adapting MLLMs for Nuanced Video Retrieval","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2603.26173","title":"ComVi: Context-Aware Optimized Comment Display in Video Playback","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2605.09904","title":"TOC-Bench: A Temporal Object Consistency Benchmark for Video Large Language Models","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.22962","title":"GazeBehavior Annotation Toolkit (GBAT): AI-powered toolkit for automatic annotation of egocentric eye-tracking and video data of child-caregiver interaction","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2605.26967","title":"CodecCap: High-Fidelity Codec-Inspired Residual Modeling for Dense Video Captioning","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.16305","title":"LookME: Lookup-Based Multimodal Embeddings for Layer Injection in Vision-Language Models","created":"2026-07-14","cited_by_count":0,"area":"mllm"},{"id":"2608.06930","title":"AVCap: Reinforcing Audio-Video Joint Caption with Detail-Aware Reward","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2609.09973","title":"Putting Captions to the Test: Evaluating Video Caption Quality through Multiple-Choice Question Answering","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.31714","title":"OmniFysics-Captioner Technical Report: Grounding Omni-Modal Understanding in the Physical World for Better Captioning","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.35090","title":"Advancing Video-Text Pretraining with Multi-View Captions","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.16066","title":"PIGEONS: Incremental Long-Video Captioning with Persistent Identity Gallery and Evolving Overarching Narrative Summary","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}