{"list":"other","total":89,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"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":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2211.09794","title":"Null-text Inversion for Editing Real Images using Guided Diffusion Models","created":"2022-11-17","cited_by_count":1179},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2303.08797","title":"Stochastic Interpolants: A Unifying Framework for Flows and Diffusions","created":"2023-03-15","cited_by_count":939},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2304.08465","title":"MasaCtrl: Tuning-Free Mutual Self-Attention Control for Consistent Image Synthesis and Editing","created":"2023-04-17","cited_by_count":727},{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"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":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"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":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2309.06380","title":"InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation","created":"2023-09-12","cited_by_count":395},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265},{"id":"2104.14806","title":"GODIVA: Generating Open-DomaIn Videos from nAtural Descriptions","created":"2021-04-30","cited_by_count":256},{"id":"2412.08629","title":"FlowEdit: Inversion-Free Text-Based Editing Using Pre-Trained Flow Models","created":"2024-12-11","cited_by_count":217},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214},{"id":"2201.00424","title":"Splicing ViT Features for Semantic Appearance Transfer","created":"2022-01-02","cited_by_count":209},{"id":"2411.04746","title":"Taming Rectified Flow for Inversion and Editing","created":"2024-11-07","cited_by_count":204},{"id":"2510.02283","title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","created":"2025-10-02","cited_by_count":192},{"id":"2410.10792","title":"Semantic Image Inversion and Editing using Rectified Stochastic Differential Equations","created":"2024-10-14","cited_by_count":165},{"id":"2403.14468","title":"AnyV2V: A Tuning-Free Framework For Any Video-to-Video Editing Tasks","created":"2024-03-21","cited_by_count":154},{"id":"2403.14602","title":"ReNoise: Real Image Inversion Through Iterative Noising","created":"2024-03-21","cited_by_count":128},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2312.10656","title":"VidToMe: Video Token Merging for Zero-Shot Video Editing","created":"2023-12-17","cited_by_count":113},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2305.04441","title":"Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models","created":"2023-05-08","cited_by_count":99},{"id":"2506.14603","title":"Align Your Flow: Scaling Continuous-Time Flow Map Distillation","created":"2025-06-17","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":"2412.18597","title":"DiTCtrl: Exploring Attention Control in Multi-Modal Diffusion Transformer for Tuning-Free Multi-Prompt Longer Video Generation","created":"2024-12-24","cited_by_count":74},{"id":"2510.09212","title":"Stable Video Infinity: Infinite-Length Video Generation with Error Recycling","created":"2025-10-10","cited_by_count":73},{"id":"2410.08151","title":"Progressive Autoregressive Video Diffusion Models","created":"2024-10-10","cited_by_count":68},{"id":"2412.07517","title":"FireFlow: Fast Inversion of Rectified Flow for Image Semantic Editing","created":"2024-12-10","cited_by_count":68},{"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":"2311.18830","title":"MotionEditor: Editing Video Motion via Content-Aware Diffusion","created":"2023-11-30","cited_by_count":57},{"id":"2502.17258","title":"VideoGrain: Modulating Space-Time Attention for Multi-grained Video Editing","created":"2025-02-24","cited_by_count":50},{"id":"2402.13185","title":"UniEdit: A Unified Tuning-Free Framework for Video Motion and Appearance Editing","created":"2024-02-20","cited_by_count":48},{"id":"2512.14699","title":"MemFlow: Flowing Adaptive Memory for Consistent and Efficient Long Video Narratives","created":"2025-12-16","cited_by_count":45},{"id":"2504.13109","title":"UniEdit-Flow: Unleashing Inversion and Editing in the Era of Flow Models","created":"2025-04-17","cited_by_count":39},{"id":"2405.15757","title":"Looking Backward: Streaming Video-to-Video Translation with Feature Banks","created":"2024-05-24","cited_by_count":38},{"id":"2411.17592","title":"VideoDirector: Precise Video Editing via Text-to-Video Models","created":"2024-11-26","cited_by_count":36},{"id":"2503.09151","title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","created":"2025-03-12","cited_by_count":35},{"id":"2505.23145","title":"FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing","created":"2025-05-29","cited_by_count":32},{"id":"2506.05046","title":"FlowDirector: Training-Free Flow Steering for Precise Text-to-Video Editing","created":"2025-06-05","cited_by_count":26},{"id":"2509.22199","title":"MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training","created":"2025-09-26","cited_by_count":25},{"id":"2506.20652","title":"EditP23: 3D Editing via Propagation of Image Prompts to Multi-View","created":"2025-06-25","cited_by_count":20},{"id":"2410.02217","title":"Stochastic Sampling from Deterministic Flow Models","created":"2024-10-03","cited_by_count":18},{"id":"2503.13684","title":"FiVE: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models","created":"2025-03-17","cited_by_count":16},{"id":"2509.22407","title":"EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer","created":"2025-09-26","cited_by_count":12},{"id":"2602.05435","title":"Stable Velocity: A Variance Perspective on Flow Matching","created":"2026-02-05","cited_by_count":12},{"id":"2511.22357","title":"AnchorFlow: Training-Free 3D Editing via Latent Anchor-Aligned Flows","created":"2025-11-27","cited_by_count":9},{"id":"2510.17803","title":"ConsistEdit: Highly Consistent and Precise Training-free Visual Editing","created":"2025-10-20","cited_by_count":6},{"id":"2511.18346","title":"FlowPortal: Residual-Corrected Flow for Training-Free Video Relighting and Background Replacement","created":"2025-11-23","cited_by_count":6},{"id":"2512.22118","title":"ProEdit: Inversion-based Editing From Prompts Done Right","created":"2025-12-26","cited_by_count":6},{"id":"2502.05433","title":"AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection","created":"2025-02-08","cited_by_count":5},{"id":"2411.10232","title":"ColorEdit: Training-free Image-Guided Color editing with diffusion model","created":"2024-11-15","cited_by_count":4},{"id":"2503.09926","title":"VideoMerge: Towards Training-free Long Video Generation","created":"2025-03-13","cited_by_count":2}],"next_cursor":null}