{"list":"other","total":73,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2511.21631","title":"Qwen3-VL Technical Report","created":"2025-11-26","cited_by_count":2793},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2410.18072","title":"WorldSimBench: Towards Video Generation Models as World Simulators","created":"2024-10-23","cited_by_count":881},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2307.16449","title":"MovieChat: From Dense Token to Sparse Memory for Long Video Understanding","created":"2023-07-31","cited_by_count":542},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2401.07519","title":"InstantID: Zero-shot Identity-Preserving Generation in Seconds","created":"2024-01-15","cited_by_count":436},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2403.14781","title":"Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance","created":"2024-03-21","cited_by_count":272},{"id":"2403.20150","title":"TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods","created":"2024-03-29","cited_by_count":249},{"id":"2405.01434","title":"StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation","created":"2024-05-02","cited_by_count":247},{"id":"2411.04746","title":"Taming Rectified Flow for Inversion and Editing","created":"2024-11-07","cited_by_count":204},{"id":"2406.01900","title":"Follow-Your-Emoji: Fine-Controllable and Expressive Freestyle Portrait Animation","created":"2024-06-04","cited_by_count":174},{"id":"2008.04838","title":"TransNet V2: An effective deep network architecture for fast shot transition detection","created":"2020-08-11","cited_by_count":171},{"id":"2402.04324","title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation","created":"2024-02-06","cited_by_count":132},{"id":"2404.15275","title":"ID-Animator: Zero-Shot Identity-Preserving Human Video Generation","created":"2024-04-23","cited_by_count":124},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2412.10859","title":"DUET: Dual Clustering Enhanced Multivariate Time Series Forecasting","created":"2024-12-14","cited_by_count":107},{"id":"2411.03286","title":"DiT4Edit: Diffusion Transformer for Image Editing","created":"2024-11-05","cited_by_count":101},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95},{"id":"2506.05207","title":"Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning","created":"2025-06-05","cited_by_count":81},{"id":"2401.09962","title":"CustomVideo: Customizing Text-to-Video Generation with Multiple Subjects","created":"2024-01-18","cited_by_count":77},{"id":"2504.02436","title":"SkyReels-A2: Compose Anything in Video Diffusion Transformers","created":"2025-04-03","cited_by_count":73},{"id":"2603.04379","title":"Helios: Real Real-Time Long Video Generation Model","created":"2026-03-04","cited_by_count":65},{"id":"2506.04590","title":"Follow-Your-Creation: Empowering 4D Creation through Video Inpainting","created":"2025-06-05","cited_by_count":62},{"id":"2510.20822","title":"HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives","created":"2025-10-23","cited_by_count":54},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48},{"id":"2510.23672","title":"DBLoss: Decomposition-based Loss Function for Time Series Forecasting","created":"2025-10-27","cited_by_count":45},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43},{"id":"2403.16407","title":"A Survey on Long Video Generation: Challenges, Methods, and Prospects","created":"2024-03-25","cited_by_count":40},{"id":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40},{"id":"2411.15262","title":"MovieBench: A Hierarchical Movie Level Dataset for Long Video Generation","created":"2024-11-22","cited_by_count":36},{"id":"2512.03041","title":"MultiShotMaster: A Controllable Multi-Shot Video Generation Framework","created":"2025-12-02","cited_by_count":36},{"id":"2404.01862","title":"Co-Speech Gesture Video Generation via Motion-Decoupled Diffusion Model","created":"2024-04-02","cited_by_count":35},{"id":"2512.07802","title":"OneStory: Coherent Multi-Shot Video Generation with Adaptive Memory","created":"2025-12-08","cited_by_count":35},{"id":"2509.14933","title":"DAG: A Dual Correlation Network for Time Series Forecasting with Exogenous Variables","created":"2025-09-18","cited_by_count":33},{"id":"2503.23307","title":"MoCha: Towards Movie-Grade Talking Character Synthesis","created":"2025-03-30","cited_by_count":31},{"id":"2506.15838","title":"EchoShot: Multi-Shot Portrait Video Generation","created":"2025-06-16","cited_by_count":29},{"id":"2508.11484","title":"CineTrans: Learning to Generate Videos with Cinematic Transitions via Masked Diffusion Models","created":"2025-08-15","cited_by_count":29},{"id":"2509.17818","title":"ContextFlow: Training-Free Video Object Editing via Adaptive Context Enrichment","created":"2025-09-22","cited_by_count":27},{"id":"2408.14211","title":"MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement","created":"2024-08-26","cited_by_count":24},{"id":"2603.26599","title":"VGGRPO: Towards World-Consistent Video Generation with 4D Latent Reward","created":"2026-03-27","cited_by_count":24},{"id":"2602.05551","title":"FastVMT: Eliminating Redundancy in Video Motion Transfer","created":"2026-02-05","cited_by_count":23},{"id":"2508.08244","title":"Cut2Next: Generating Next Shot via In-Context Tuning","created":"2025-08-11","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":"2607.08766","title":"OPSD-V: On-Policy Self-Distillation for Post-Training Few-Step Autoregressive Video Generators","created":"2026-07-09","cited_by_count":14},{"id":"2412.06340","title":"UniPaint: Unified Space-time Video Inpainting via Mixture-of-Experts","created":"2024-12-09","cited_by_count":13},{"id":"2603.22883","title":"Group Editing: Edit Multiple Images in One Go","created":"2026-03-24","cited_by_count":11},{"id":"2512.12193","title":"SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation","created":"2025-12-13","cited_by_count":10},{"id":"2503.12047","title":"PSGait: Gait Recognition using Parsing Skeleton","created":"2025-03-15","cited_by_count":8},{"id":"2503.18830","title":"DAGait: Generalized Skeleton-Guided Data Alignment for Gait Recognition","created":"2025-03-24","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":"2605.17312","title":"VISTA: Triplet-Supervised Video Style Transfer with Diffusion Transformers","created":"2026-05-17","cited_by_count":8},{"id":"2606.01399","title":"PAI-Studio: Cinematic Video Background Replacement with Camera-Aware Motion","created":"2026-05-31","cited_by_count":8},{"id":"2508.07597","title":"ShoulderShot: Generating Over-the-Shoulder Dialogue Videos","created":"2025-08-11","cited_by_count":7},{"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},{"id":"2601.11931","title":"Language-Guided and Motion-Aware Gait Representation for Generalizable Recognition","created":"2026-01-17","cited_by_count":7},{"id":"2602.03796","title":"3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation","created":"2026-02-03","cited_by_count":6},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5},{"id":"2606.27974","title":"ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering","created":"2026-06-26","cited_by_count":5},{"id":"2512.25066","title":"From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping","created":"2025-12-31","cited_by_count":3},{"id":"2606.19805","title":"ParaScale: Scale-Calibrated Camera-Motion Transfer via a Gauge-Invariant Parallax Number","created":"2026-06-18","cited_by_count":2}],"next_cursor":null}