{"list":"other","total":56,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","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":"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":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2506.08009","title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","created":"2025-06-09","cited_by_count":625},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"2502.10248","title":"Step-Video-T2V Technical Report: The Practice, Challenges, and Future of Video Foundation Model","created":"2025-02-14","cited_by_count":168},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143},{"id":"2405.11473","title":"FIFO-Diffusion: Generating Infinite Videos from Text without Training","created":"2024-05-19","cited_by_count":137},{"id":"2503.05638","title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","created":"2025-03-07","cited_by_count":125},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"2410.19355","title":"FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality","created":"2024-10-25","cited_by_count":122},{"id":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2503.10592","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models","created":"2025-03-13","cited_by_count":98},{"id":"2506.17201","title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","created":"2025-06-20","cited_by_count":98},{"id":"2312.09109","title":"VideoLCM: Video Latent Consistency Model","created":"2023-12-14","cited_by_count":92},{"id":"2405.18750","title":"T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback","created":"2024-05-29","cited_by_count":87},{"id":"2512.22096","title":"Yume-1.5: A Text-Controlled Interactive World Generation Model","created":"2025-12-26","cited_by_count":84},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80},{"id":"2511.01266","title":"MotionStream: Real-Time Video Generation with Interactive Motion Controls","created":"2025-11-03","cited_by_count":76},{"id":"2510.09212","title":"Stable Video Infinity: Infinite-Length Video Generation with Error Recycling","created":"2025-10-10","cited_by_count":73},{"id":"2411.05003","title":"ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning","created":"2024-11-07","cited_by_count":70},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65},{"id":"2602.06028","title":"Context Forcing: Consistent Autoregressive Video Generation with Long Context","created":"2026-02-05","cited_by_count":59},{"id":"2309.03549","title":"Reuse and Diffuse: Iterative Denoising for Text-to-Video Generation","created":"2023-09-07","cited_by_count":50},{"id":"2507.03745","title":"StreamDiT: Real-Time Streaming Text-to-Video Generation","created":"2025-07-04","cited_by_count":48},{"id":"2506.03140","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation","created":"2025-06-03","cited_by_count":46},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44},{"id":"2512.04519","title":"VideoSSM: Autoregressive Long Video Generation with Hybrid State-Space Memory","created":"2025-12-04","cited_by_count":42},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40},{"id":"2412.00887","title":"Playable Game Generation","created":"2024-12-01","cited_by_count":26},{"id":"2603.21366","title":"Relax Forcing: Relaxed KV-Memory for Consistent Long Video Generation","created":"2026-03-22","cited_by_count":24},{"id":"2303.13472","title":"Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models","created":"2023-03-23","cited_by_count":22},{"id":"2508.15720","title":"WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception","created":"2025-08-21","cited_by_count":16},{"id":"2512.05076","title":"BulletTime: Decoupled Control of Time and Camera Pose for Video Generation","created":"2025-12-04","cited_by_count":14},{"id":"2412.06029","title":"Latent-Reframe: Enabling Camera Control for Video Diffusion Model without Training","created":"2024-12-08","cited_by_count":13},{"id":"2511.12940","title":"Recurrent Autoregressive Diffusion: Global Memory Meets Local Attention","created":"2025-11-17","cited_by_count":9},{"id":"2512.12430","title":"Endless World: Real-Time 3D-Aware Long Video Generation","created":"2025-12-13","cited_by_count":4},{"id":"2605.20476","title":"Goodbye Drift: Anchored Tree Sampling for Long-Horizon Video-to-Video Generation","created":"2026-05-19","cited_by_count":2}],"next_cursor":null}