{"list":"other","total":70,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"2203.12602","title":"VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training","created":"2022-03-23","cited_by_count":1322},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"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":"2410.06940","title":"Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think","created":"2024-10-09","cited_by_count":703},{"id":"2410.13720","title":"Movie Gen: A Cast of Media Foundation Models","created":"2024-10-17","cited_by_count":644},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2303.16727","title":"VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking","created":"2023-03-29","cited_by_count":528},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"id":"2305.13077","title":"ControlVideo: Training-free Controllable Text-to-Video Generation","created":"2023-05-22","cited_by_count":327},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2306.07954","title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","created":"2023-06-13","cited_by_count":253},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2504.10483","title":"REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers","created":"2025-04-14","cited_by_count":225},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2004.06130","title":"SpeedNet: Learning the Speediness in Videos","created":"2020-04-13","cited_by_count":171},{"id":"2310.05922","title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","created":"2023-10-09","cited_by_count":167},{"id":"1811.09795","title":"Self-Supervised Video Representation Learning with Space-Time Cubic Puzzles","created":"2018-11-24","cited_by_count":149},{"id":"2008.05861","title":"Self-supervised Video Representation Learning by Pace Prediction","created":"2020-08-13","cited_by_count":139},{"id":"2410.08260","title":"Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content","created":"2024-10-10","cited_by_count":135},{"id":"2006.11476","title":"Video Playback Rate Perception for Self-supervisedSpatio-Temporal Representation Learning","created":"2020-06-20","cited_by_count":103},{"id":"2505.23656","title":"VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models","created":"2025-05-29","cited_by_count":98},{"id":"2405.04007","title":"SEED-Data-Edit Technical Report: A Hybrid Dataset for Instructional Image Editing","created":"2024-05-07","cited_by_count":97},{"id":"2510.08377","title":"UniVideo: Unified Understanding, Generation, and Editing for Videos","created":"2025-10-09","cited_by_count":87},{"id":"2311.00213","title":"Consistent Video-to-Video Transfer Using Synthetic Dataset","created":"2023-11-01","cited_by_count":81},{"id":"2510.15742","title":"Scaling Instruction-Based Video Editing with a High-Quality Synthetic Dataset","created":"2025-10-17","cited_by_count":79},{"id":"2501.10018","title":"DiffuEraser: A Diffusion Model for Video Inpainting","created":"2025-01-17","cited_by_count":72},{"id":"2512.16776","title":"Kling-Omni Technical Report","created":"2025-12-18","cited_by_count":71},{"id":"2501.02955","title":"MotionBench: Benchmarking and Improving Fine-grained Video Motion Understanding for Vision Language Models","created":"2025-01-06","cited_by_count":70},{"id":"2507.21033","title":"GPT-IMAGE-EDIT-1.5M: A Million-Scale, GPT-Generated Image Dataset","created":"2025-07-28","cited_by_count":70},{"id":"2503.20287","title":"InsViE-1M: Effective Instruction-based Video Editing with Elaborate Dataset Construction","created":"2025-03-26","cited_by_count":62},{"id":"2502.06734","title":"Se\\~norita-2M: A High-Quality Instruction-based Dataset for General Video Editing by Video Specialists","created":"2025-02-10","cited_by_count":61},{"id":"2510.19808","title":"Pico-Banana-400K: A Large-Scale Dataset for Text-Guided Image Editing","created":"2025-10-22","cited_by_count":61},{"id":"2505.02831","title":"No Other Representation Component Is Needed: Diffusion Transformers Can Provide Representation Guidance by Themselves","created":"2025-05-05","cited_by_count":56},{"id":"2506.04216","title":"UNIC: Unified In-Context Video Editing","created":"2025-06-04","cited_by_count":55},{"id":"2509.20360","title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","created":"2025-09-24","cited_by_count":54},{"id":"2506.05083","title":"SeedEdit 3.0: Fast and High-Quality Generative Image Editing","created":"2025-06-05","cited_by_count":53},{"id":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53},{"id":"2305.13840","title":"Control-A-Video: Controllable Text-to-Video Diffusion Models with Motion Prior and Reward Feedback Learning","created":"2023-05-23","cited_by_count":48},{"id":"2505.24873","title":"MiniMax-Remover: Taming Bad Noise Helps Video Object Removal","created":"2025-05-30","cited_by_count":45},{"id":"2507.06119","title":"Omni-Video: Democratizing Unified Video Understanding and Generation","created":"2025-07-08","cited_by_count":40},{"id":"2505.16792","title":"REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training","created":"2025-05-22","cited_by_count":37},{"id":"2306.08707","title":"VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing","created":"2023-06-14","cited_by_count":36},{"id":"2510.14648","title":"In-Context Learning with Unpaired Clips for Instruction-based Video Editing","created":"2025-10-16","cited_by_count":35},{"id":"2507.14119","title":"NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining","created":"2025-07-18","cited_by_count":33},{"id":"2510.08485","title":"InstructX: Towards Unified Visual Editing with MLLM Guidance","created":"2025-10-09","cited_by_count":32},{"id":"2601.02358","title":"VINO: A Unified Visual Generator with Interleaved OmniModal Context","created":"2026-01-05","cited_by_count":26},{"id":"2508.07607","title":"X2Edit: Revisiting Arbitrary-Instruction Image Editing through Self-Constructed Data and Task-Aware Representation Learning","created":"2025-08-11","cited_by_count":25},{"id":"2512.17650","title":"Region-Constraint In-Context Generation for Instructional Video Editing","created":"2025-12-19","cited_by_count":23},{"id":"2509.26641","title":"Query-Kontext: An Unified Multimodal Model for Image Generation and Editing","created":"2025-09-30","cited_by_count":15},{"id":"2210.05234","title":"It Takes Two: Masked Appearance-Motion Modeling for Self-supervised Video Transformer Pre-training","created":"2022-10-11","cited_by_count":10},{"id":"2512.20619","title":"SemanticGen: Video Generation in Semantic Space","created":"2025-12-23","cited_by_count":6},{"id":"2601.01720","title":"FFP-300K: Scaling First-Frame Propagation for Generalizable Video Editing","created":"2026-01-05","cited_by_count":5},{"id":"2412.18525","title":"Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization","created":"2024-12-24","cited_by_count":4},{"id":"2602.22150","title":"CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation","created":"2026-02-25","cited_by_count":3}],"next_cursor":null}