{"total":74,"rows":[{"id":"2505.11709","title":"EgoDex: Learning Dexterous Manipulation from Large-Scale Egocentric Video","created":"2025-05-16","cited_by_count":211,"area":null},{"id":"2505.20292","title":"OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation","created":"2025-05-26","cited_by_count":73,"area":null},{"id":"2602.08794","title":"MOVA: Towards Scalable and Synchronized Video-Audio Generation","created":"2026-02-09","cited_by_count":43,"area":null},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40,"area":null},{"id":"2507.13428","title":"\"PhyWorldBench\": A Comprehensive Evaluation of Physical Realism in Text-to-Video Models","created":"2025-07-17","cited_by_count":36,"area":null},{"id":"2601.16914","title":"LoL: Longer than Longer, Scaling Video Generation to Hour","created":"2026-01-23","cited_by_count":32,"area":null},{"id":"2509.14476","title":"AToken: A Unified Tokenizer for Vision","created":"2025-09-17","cited_by_count":30,"area":null},{"id":"2510.01784","title":"Pack and Force Your Memory: Long-form and Consistent Video Generation","created":"2025-10-02","cited_by_count":29,"area":null},{"id":"2508.07901","title":"Stand-In: A Lightweight and Plug-and-Play Identity Control for Video Generation","created":"2025-08-11","cited_by_count":28,"area":null},{"id":"2510.01174","title":"Code2Video: A Code-centric Paradigm for Educational Video Generation","created":"2025-10-01","cited_by_count":27,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2509.25182","title":"DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder","created":"2025-09-29","cited_by_count":16,"area":null},{"id":"2601.11035","title":"Your One-Stop Solution for AI-Generated Video Detection","created":"2026-01-16","cited_by_count":15,"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":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"area":null},{"id":"2505.14709","title":"FastCar: Cache Attentive Replay for Fast Auto-Regressive Video Generation on the Edge","created":"2025-05-17","cited_by_count":10,"area":null},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"id":"2506.18901","title":"From Virtual Games to Real-World Play","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2510.14847","title":"ImagerySearch: Adaptive Test-Time Search for Video Generation Beyond Semantic Dependency Constraints","created":"2025-10-16","cited_by_count":9,"area":null},{"id":"2511.12940","title":"Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention","created":"2025-11-17","cited_by_count":9,"area":null},{"id":"2605.26244","title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","created":"2026-05-25","cited_by_count":9,"area":null},{"id":"2510.05097","title":"Pulp Motion: Framing-aware multimodal camera and human motion generation","created":"2025-10-06","cited_by_count":8,"area":null},{"id":"2602.10113","title":"ConsID-Gen: View-Consistent and Identity-Preserving Image-to-Video Generation","created":"2026-02-10","cited_by_count":8,"area":null},{"id":"2512.07831","title":"UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2506.08456","title":"Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance","created":"2025-06-10","cited_by_count":6,"area":null},{"id":"2507.07202","title":"A Survey on Long-Video Storytelling Generation: Architectures, Consistency, and Cinematic Quality","created":"2025-07-09","cited_by_count":6,"area":null},{"id":"2605.01725","title":"Motion-Aware Caching for Efficient Autoregressive Video Generation","created":"2026-05-03","cited_by_count":6,"area":null},{"id":"2509.21917","title":"Taming Flow-based I2V Models for Creative Video Editing","created":"2025-09-26","cited_by_count":5,"area":null},{"id":"2512.21252","title":"DreaMontage: Arbitrary Frame-Guided One-Shot Video Generation","created":"2025-12-24","cited_by_count":5,"area":null},{"id":"2603.08403","title":"SPIRAL: Self-Evolving Action-Conditioned Video Generation via Reflective Planning Agents","created":"2026-03-09","cited_by_count":5,"area":null},{"id":"2607.13336","title":"Delving into the Temporal Challenges of Unified Video Protection Against Image-to-Video and Fine-Tuning-based Customization","created":"2026-07-14","cited_by_count":5,"area":null},{"id":"2512.22536","title":"CoAgent: Collaborative Planning and Consistency Agent for Coherent Video Generation","created":"2025-12-27","cited_by_count":4,"area":null},{"id":"2511.16957","title":"MatPedia: A Universal Generative Foundation for High-Fidelity Material Synthesis","created":"2025-11-21","cited_by_count":3,"area":null},{"id":"2512.05103","title":"TV2TV: A Unified Framework for Interleaved Language and Video Generation","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2601.20504","title":"Latent Temporal Discrepancy as Motion Prior: A Loss-Weighting Strategy for Dynamic Fidelity in T2V","created":"2026-01-28","cited_by_count":3,"area":null},{"id":"2602.04202","title":"VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents","created":"2026-02-04","cited_by_count":3,"area":null},{"id":"2607.14088","title":"VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders","created":"2026-07-15","cited_by_count":3,"area":null},{"id":"2607.18924","title":"Learning Explicit Physical Parameter Control and Benchmarking for Video Generation","created":"2026-07-21","cited_by_count":3,"area":null},{"id":"2609.07720","title":"Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation","created":"2026-09-07","cited_by_count":3,"area":null},{"id":"2506.04715","title":"Towards Holistic Visual Quality Assessment of AI-Generated Videos: A LLM-Based Multi-Dimensional Evaluation Model","created":"2025-06-05","cited_by_count":2,"area":null},{"id":"2512.13281","title":"VideoASMR-Bench: Can AI-Generated ASMR Videos Fool VLMs and Humans?","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2512.22317","title":"LangPrecip: Language-Aware Multimodal Precipitation Nowcasting","created":"2025-12-26","cited_by_count":2,"area":null},{"id":"2604.01207","title":"TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2510.03049","title":"When and Where do Events Switch in Multi-Event Video Generation?","created":"2025-10-03","cited_by_count":1,"area":null},{"id":"2511.17344","title":"Loomis Painter: Reconstructing the Painting Process","created":"2025-11-21","cited_by_count":1,"area":null},{"id":"2511.19319","title":"SyncMV4D: Synchronized Multi-view Joint Diffusion of Appearance and Motion for Hand-Object Interaction Synthesis","created":"2025-11-24","cited_by_count":1,"area":null},{"id":"2512.11293","title":"Autoregressive Video Autoencoder with Decoupled Temporal and Spatial Context","created":"2025-12-12","cited_by_count":1,"area":null},{"id":"2512.12209","title":"CineLOG: A Training Free Approach for Cinematic Long Video Generation","created":"2025-12-13","cited_by_count":1,"area":null},{"id":"2512.21019","title":"Efficient and Robust Video Defense Framework against 3D-field Personalized Talking Face","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2512.21276","title":"GriDiT: Factorized Grid-Based Diffusion for Efficient Long Image Sequence Generation","created":"2025-12-24","cited_by_count":1,"area":null},{"id":"2602.12128","title":"HLA: Hadamard Linear Attention","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2604.15299","title":"AnimationBench: Are Video Models Good at Character-Centric Animation?","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2604.24416","title":"Scaling Properties of Continuous Diffusion Spoken Language Models","created":"2026-04-27","cited_by_count":1,"area":null},{"id":"2606.13872","title":"Avatar V: Scaling Video-Reference Avatar Video Generation","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.24829","title":"GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction","created":"2026-06-23","cited_by_count":1,"area":null},{"id":"2609.12874","title":"VideoTok4D: A 4D-Aware Video Tokenizer for Compact World Representation","created":"2026-09-11","cited_by_count":1,"area":null},{"id":"2506.22868","title":"STR-Match: Matching SpatioTemporal Relevance Score for Training-Free Video Editing","created":"2025-06-28","cited_by_count":0,"area":null},{"id":"2508.08891","title":"Preview WB-DH: Towards Whole Body Digital Human Bench for the Generation of Whole-body Talking Avatar Videos","created":"2025-08-12","cited_by_count":0,"area":null},{"id":"2510.17519","title":"MUG-V 10B: High-efficiency Training Pipeline for Large Video Generation Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2510.20182","title":"PEDRA: Evaluating the Realism of Pedestrian Dynamics in Video Generation","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.08439","title":"Dataset Safety in Autonomous Driving: Requirements, Risks, and Assurance","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.11480","title":"CADMorph: Geometry-Driven Parametric CAD Editing via a Plan-Generate-Verify Loop","created":"2025-12-12","cited_by_count":0,"area":null},{"id":"2601.19236","title":"VC-Bench: Pioneering the Video Connecting Benchmark with a Dataset and Evaluation Metrics","created":"2026-01-27","cited_by_count":0,"area":null},{"id":"2602.17260","title":"EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection","created":"2026-02-19","cited_by_count":0,"area":null},{"id":"2603.22091","title":"P-Flow: Prompting Visual Effects Generation","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.26866","title":"LACON: Training Text-to-Image Model from Uncurated Data","created":"2026-03-27","cited_by_count":0,"area":null},{"id":"2604.16503","title":"Motif-Video 2B: Technical Report","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2604.17565","title":"UniGeo: Unifying Geometric Guidance for Camera-Controllable Image Editing via Video Models","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2606.00967","title":"MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2607.02584","title":"RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2609.06652","title":"VidaForge: Open Research Infrastructure for Video Pretraining Data Recipes","created":"2026-09-06","cited_by_count":0,"area":null},{"id":"2609.40356","title":"ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text Editing","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.07939","title":"CCDF: A Benchmark Dataset for Deepfake Detection in Real-World Surveillance Footage","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13733","title":"KVeil: First-Place Solution to ECCV 2026 LifeGenIP Challenge on Unlearnable Videos","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}