{"total":82,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429,"area":null},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2501.15368","title":"Baichuan-Omni-1.5 Technical Report","created":"2025-01-26","cited_by_count":111,"area":null},{"id":"2503.08153","title":"WISA: World Simulator Assistant for Physics-Aware Text-to-Video Generation","created":"2025-03-11","cited_by_count":90,"area":null},{"id":"2505.04512","title":"HunyuanCustom: A Multimodal-Driven Architecture for Customized Video Generation","created":"2025-05-07","cited_by_count":87,"area":null},{"id":"2412.00115","title":"OpenHumanVid: A Large-Scale High-Quality Dataset for Enhancing Human-Centric Video Generation","created":"2024-11-28","cited_by_count":77,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"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":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69,"area":null},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66,"area":null},{"id":"2508.18621","title":"Wan-S2V: Audio-Driven Cinematic Video Generation","created":"2025-08-26","cited_by_count":61,"area":null},{"id":"2502.10059","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","created":"2025-02-14","cited_by_count":57,"area":null},{"id":"2506.13691","title":"UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions","created":"2025-06-16","cited_by_count":57,"area":null},{"id":"2607.07534","title":"Infinite Worlds with Versatile Interactions","created":"2026-07-08","cited_by_count":48,"area":null},{"id":"2509.08519","title":"HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning","created":"2025-09-10","cited_by_count":47,"area":null},{"id":"2506.03140","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation","created":"2025-06-03","cited_by_count":46,"area":null},{"id":"2509.22799","title":"VideoScore2: Think before You Score in Generative Video Evaluation","created":"2025-09-26","cited_by_count":40,"area":null},{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"id":"2510.11647","title":"IVEBench: Modern Benchmark Suite for Instruction-Guided Video Editing Assessment","created":"2025-10-13","cited_by_count":28,"area":null},{"id":"2512.21334","title":"Streaming Video Instruction Tuning","created":"2025-12-24","cited_by_count":26,"area":null},{"id":"2502.12782","title":"VidCapBench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation","created":"2025-02-18","cited_by_count":23,"area":null},{"id":"2503.01739","title":"VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation","created":"2025-03-03","cited_by_count":21,"area":null},{"id":"2506.18851","title":"Phantom-Data : Towards a General Subject-Consistent Video Generation Dataset","created":"2025-06-23","cited_by_count":17,"area":null},{"id":"2507.00162","title":"FreeLong++: Training-Free Long Video Generation via Multi-band SpectralFusion","created":"2025-06-30","cited_by_count":17,"area":null},{"id":"2506.07848","title":"PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement","created":"2025-06-09","cited_by_count":16,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2504.08212","title":"RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements","created":"2025-04-11","cited_by_count":14,"area":null},{"id":"2601.02204","title":"NextFlow: Unified Sequential Modeling Activates Multimodal Understanding and Generation","created":"2026-01-05","cited_by_count":14,"area":null},{"id":"2601.10592","title":"Action100M: A Large-scale Video Action Dataset","created":"2026-01-15","cited_by_count":12,"area":null},{"id":"2602.21818","title":"SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2502.03207","title":"MotionAgent: Fine-grained Controllable Video Generation via Motion Field Agent","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2510.09987","title":"Generative Latent Video Compression","created":"2025-10-11","cited_by_count":11,"area":null},{"id":"2503.24379","title":"Any2Caption:Interpreting Any Condition to Caption for Controllable Video Generation","created":"2025-03-31","cited_by_count":10,"area":null},{"id":"2511.23428","title":"DisMo: Disentangled Motion Representations for Open-World Motion Transfer","created":"2025-11-28","cited_by_count":10,"area":null},{"id":"2512.06905","title":"Scaling Zero-Shot Reference-to-Video Generation","created":"2025-12-07","cited_by_count":9,"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":"2603.19228","title":"SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing","created":"2026-03-19","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":"2605.18733","title":"Advancing Narrative Long Video Generation via Training-Free Identity-Aware Memory","created":"2026-05-18","cited_by_count":7,"area":null},{"id":"2503.06053","title":"DropletVideo: A Dataset and Approach to Explore Integral Spatio-Temporal Consistent Video Generation","created":"2025-03-08","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":"2601.10632","title":"CoMoVi: Co-Generation of 3D Human Motions and Realistic Videos","created":"2026-01-15","cited_by_count":6,"area":null},{"id":"2606.06042","title":"LoomVideo: Unifying Multimodal Inputs into Video Generation and Editing","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2606.09639","title":"CineDance: Towards Next-Generation Multi-Shot Long-Form Cinematic Audio-Video Generation","created":"2026-06-08","cited_by_count":6,"area":null},{"id":"2606.30599","title":"Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2510.08555","title":"VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning","created":"2025-10-09","cited_by_count":5,"area":null},{"id":"2512.13465","title":"PoseAnything: Universal Pose-guided Video Generation with Part-aware Temporal Coherence","created":"2025-12-15","cited_by_count":5,"area":null},{"id":"2601.01720","title":"FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing","created":"2026-01-05","cited_by_count":5,"area":null},{"id":"2603.01685","title":"FastLightGen: Fast and Light Video Generation with Fewer Steps and Parameters","created":"2026-03-02","cited_by_count":5,"area":null},{"id":"2604.24762","title":"OmniShotCut: Holistic Relational Shot Boundary Detection with Shot-Query Transformer","created":"2026-04-27","cited_by_count":5,"area":null},{"id":"2507.01938","title":"CI-VID: A Coherent Interleaved Text-Video Dataset","created":"2025-07-02","cited_by_count":4,"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":"2603.25527","title":"Beyond the Golden Data: Resolving the Motion-Vision Quality Dilemma via Timestep Selective Training","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2608.01113","title":"CoT-Edit: Let CoT Guide Instruction Video Editing","created":"2026-08-02","cited_by_count":3,"area":null},{"id":"2507.13345","title":"Imbalance in Balance: Online Concept Balancing in Generation Models","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2509.11589","title":"MVQA-68K: A Multi-dimensional and Causally-annotated Dataset with Quality Interpretability for Video Assessment","created":"2025-09-15","cited_by_count":2,"area":null},{"id":"2603.06688","title":"Narrative Weaver: Towards Controllable Long-Range Visual Consistency with Multi-Modal Conditioning","created":"2026-03-04","cited_by_count":2,"area":null},{"id":"2606.03168","title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","created":"2026-06-02","cited_by_count":2,"area":null},{"id":"2606.09770","title":"Discovering Functionally Selective Brain Regions with a Deep Topographic Multimodal Model","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2606.20774","title":"TriMotion: Modality-Agnostic Camera Control for Video Generation","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2504.15182","title":"Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platform","created":"2025-04-21","cited_by_count":1,"area":null},{"id":"2505.20827","title":"Frame-Level Captions for Long Video Generation with Complex Multi Scenes","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2507.05173","title":"Semantic Frame Interpolation","created":"2025-07-07","cited_by_count":1,"area":null},{"id":"2604.07990","title":"SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2604.11737","title":"Learning Long-term Motion Embeddings for Efficient Kinematics Generation","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2608.17426","title":"SemComp-Bench: Benchmarking Semantic Task Completion in Video Generation","created":"2026-08-18","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":"2508.09476","title":"Collaborative Face Experts Fusion in Video Generation: Boosting Identity Consistency Across Large Face Poses","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2509.09151","title":"Video Understanding by Design: How Datasets Shape Video Models","created":"2025-09-11","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":"2602.16231","title":"DataCube: A Video Retrieval Platform via Natural Language Semantic Profiling","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.05539","title":"VDCook:DIY video data cook your MLLMs","created":"2026-03-04","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":"2606.31326","title":"Bridging Video Understanding and Generation in a Unified Framework","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.25642","title":"Instruction-based Image Editing: A Survey on Data, Models, Evaluation, and Applications","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.25984","title":"Schr\\\"odinger's Cat: Probabilistic Representation and Prediction of Potential Scene Kinematics","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.31106","title":"DreamX-Creator: Democratizing Native Audio-Video Generation at 2K Resolution","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.22069","title":"OmniVBench: A Benchmark and Large-Scale Dataset for Omni Reference-to-Video Generation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.29225","title":"ComplexSync: High-Fidelity and Real-Time Lip Sync in Complex Scenarios","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.03691","title":"FlowHMR: Physically Plausible Motion Capture from Video","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.05587","title":"Generating the Wild: Individual-Consistent Image-to-Video Generation for Wildlife","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}