{"list":"other","total":69,"rows":[{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2212.04089","title":"Editing Models with Task Arithmetic","created":"2022-12-08","cited_by_count":1120},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2109.01903","title":"Robust fine-tuning of zero-shot models","created":"2021-09-04","cited_by_count":797},{"id":"2210.03142","title":"On Distillation of Guided Diffusion Models","created":"2022-10-06","cited_by_count":725},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2602.15922","title":"World Action Models are Zero-shot Policies","created":"2026-02-17","cited_by_count":465},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"id":"2603.16666","title":"Fast-WAM: Do World Action Models Need Test-time Future Imagination?","created":"2026-03-17","cited_by_count":349},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"2512.13030","title":"Motus: A Unified Latent Action World Model","created":"2025-12-15","cited_by_count":251},{"id":"2311.05556","title":"LCM-LoRA: A Universal Stable-Diffusion Acceleration Module","created":"2023-11-09","cited_by_count":211},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2602.06949","title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","created":"2026-02-06","cited_by_count":135},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106},{"id":"2510.01284","title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","created":"2025-09-30","cited_by_count":83},{"id":"2504.04842","title":"FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis","created":"2025-04-07","cited_by_count":77},{"id":"2505.20156","title":"HunyuanVideo-Avatar: High-Fidelity Audio-Driven Human Animation for Multiple Characters","created":"2025-05-26","cited_by_count":69},{"id":"2505.22647","title":"Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation","created":"2025-05-28","cited_by_count":66},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45},{"id":"2505.22944","title":"ATI: Any Trajectory Instruction for Controllable Video Generation","created":"2025-05-28","cited_by_count":43},{"id":"2510.12747","title":"FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution","created":"2025-10-14","cited_by_count":43},{"id":"2508.14033","title":"InfiniteTalk: Audio-driven Video Generation for Sparse-Frame Video Dubbing","created":"2025-08-19","cited_by_count":41},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40},{"id":"2606.16993","title":"DreamX-World 1.0: A General-Purpose Interactive World Model","created":"2026-06-15","cited_by_count":40},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38},{"id":"2511.03334","title":"UniAVGen: Unified Audio and Video Generation with Asymmetric Cross-Modal Interactions","created":"2025-11-05","cited_by_count":38},{"id":"2603.02175","title":"Kiwi-Edit: Versatile Video Editing via Instruction and Reference Guidance","created":"2026-03-02","cited_by_count":36},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34},{"id":"2603.23376","title":"ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignment","created":"2026-03-24","cited_by_count":29},{"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},{"id":"2512.22065","title":"StreamAvatar: Streaming Diffusion Models for Real-Time Interactive Human Avatars","created":"2025-12-26","cited_by_count":25},{"id":"2505.23742","title":"MAGREF: Masked Guidance for Any-Reference Video Generation with Subject Disentanglement","created":"2025-05-29","cited_by_count":23},{"id":"2601.23286","title":"VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation","created":"2026-01-30","cited_by_count":23},{"id":"2601.11087","title":"PhysRVG: Physics-Aware Unified Reinforcement Learning for Video Generative Models","created":"2026-01-16","cited_by_count":17},{"id":"2406.01954","title":"Plug-and-Play Diffusion Distillation","created":"2024-06-04","cited_by_count":16},{"id":"2505.21325","title":"MagicTryOn: Harnessing Diffusion Transformer for Garment-Preserving Video Virtual Try-on","created":"2025-05-27","cited_by_count":15},{"id":"2606.26740","title":"LiveEdit: Towards Real-Time Diffusion-Based Streaming Video Editing","created":"2026-06-25","cited_by_count":15},{"id":"2608.25927","title":"Code World Model: Coding Agent as World Brain","created":"2026-08-26","cited_by_count":14},{"id":"2605.23345","title":"SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models","created":"2026-05-22","cited_by_count":13},{"id":"2605.27817","title":"Turning Video Models into Generalist Robot Policies","created":"2026-05-27","cited_by_count":12},{"id":"2609.02886","title":"SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models","created":"2026-09-02","cited_by_count":12},{"id":"2505.21491","title":"Frame In-N-Out: Unbounded Controllable Image-to-Video Generation","created":"2025-05-27","cited_by_count":10},{"id":"2608.23565","title":"ReWorld: An Interactive World Model with Long-Horizon Memory","created":"2026-08-24","cited_by_count":10},{"id":"2512.13604","title":"LongVie 2: Multimodal Controllable Ultra-Long Video World Model","created":"2025-12-15","cited_by_count":9},{"id":"2605.15256","title":"ReactiveGWM: Steering NPC in Reactive Game World Models","created":"2026-05-14","cited_by_count":9},{"id":"2412.10255","title":"AniSora: Exploring the Frontiers of Animation Video Generation in the Sora Era","created":"2024-12-13","cited_by_count":8},{"id":"2512.07469","title":"VideoCoF: Unified Video Editing with Temporal Reasoner","created":"2025-12-08","cited_by_count":8},{"id":"2603.19228","title":"SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing","created":"2026-03-19","cited_by_count":8},{"id":"2605.17019","title":"StreamingEffect: Real-Time Human-Centric Video Effect Generation","created":"2026-05-16","cited_by_count":8},{"id":"2509.24979","title":"Video Generation with Stable Transparency via Shiftable RGB-A Distribution Learner","created":"2025-09-29","cited_by_count":7},{"id":"2605.30073","title":"Native Audio-Visual Alignment for Generation","created":"2026-05-28","cited_by_count":7},{"id":"2503.07274","title":"Efficient Distillation of Classifier-Free Guidance using Adapters","created":"2025-03-10","cited_by_count":6},{"id":"2606.10135","title":"BiWM: Advancing Open-Source Interactive Video World Models with Bidirectional Autoregression","created":"2026-06-08","cited_by_count":6},{"id":"2603.12146","title":"FlashMotion: Few-Step Controllable Video Generation with Trajectory Guidance","created":"2026-03-12","cited_by_count":5},{"id":"2609.01560","title":"H3-World: Turning Language Understanding into World Control","created":"2026-09-01","cited_by_count":4},{"id":"2512.14938","title":"TalkVerse: Democratizing Minute-Long Audio-Driven Video Generation","created":"2025-12-16","cited_by_count":3},{"id":"2602.12304","title":"OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model","created":"2026-02-12","cited_by_count":3},{"id":"2607.29302","title":"BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning","created":"2026-07-31","cited_by_count":3},{"id":"2511.17344","title":"Loomis Painter: Reconstructing the Painting Process","created":"2025-11-21","cited_by_count":1},{"id":"2607.14976","title":"From Draft to Draft-Free: One-Step Video Object Removal via Privileged Distillation and Fast Planting","created":"2026-07-16","cited_by_count":1}],"next_cursor":null}