{"list":"other","total":72,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"1711.05101","title":"Decoupled Weight Decay Regularization","created":"2017-11-14","cited_by_count":1831},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"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":"2305.01569","title":"Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation","created":"2023-05-02","cited_by_count":977},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"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":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"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":"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":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2307.06942","title":"InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation","created":"2023-07-13","cited_by_count":497},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"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":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2505.09568","title":"BLIP3-o: A Family of Fully Open Unified Multimodal Models-Architecture, Training and Dataset","created":"2025-05-14","cited_by_count":376},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2505.20275","title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","created":"2025-05-26","cited_by_count":231},{"id":"2504.20690","title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer","created":"2025-04-29","cited_by_count":204},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2404.09990","title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","created":"2024-04-15","cited_by_count":193},{"id":"2303.07399","title":"RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose","created":"2023-03-13","cited_by_count":175},{"id":"2310.01506","title":"Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code","created":"2023-10-02","cited_by_count":145},{"id":"2411.07199","title":"OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision","created":"2024-11-11","cited_by_count":145},{"id":"2505.22705","title":"HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer","created":"2025-05-28","cited_by_count":141},{"id":"2303.17599","title":"Zero-Shot Video Editing Using Off-The-Shelf Image Diffusion Models","created":"2023-03-30","cited_by_count":137},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124},{"id":"2304.04269","title":"HumanSD: A Native Skeleton-Guided Diffusion Model for Human Image Generation","created":"2023-04-09","cited_by_count":105},{"id":"2412.07774","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","created":"2024-12-10","cited_by_count":102},{"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":"2506.18095","title":"ShareGPT-4o-Image: Aligning Multimodal Models with GPT-4o-Level Image Generation","created":"2025-06-22","cited_by_count":97},{"id":"2311.00213","title":"Consistent Video-to-Video Transfer Using Synthetic Dataset","created":"2023-11-01","cited_by_count":81},{"id":"2501.10018","title":"DiffuEraser: A Diffusion Model for Video Inpainting","created":"2025-01-17","cited_by_count":72},{"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":"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":"2310.16003","title":"CVPR 2023 Text Guided Video Editing Competition","created":"2023-10-24","cited_by_count":55},{"id":"2506.04216","title":"UNIC: Unified In-Context Video Editing","created":"2025-06-04","cited_by_count":55},{"id":"2503.19907","title":"FullDiT: Multi-Task Video Generative Foundation Model with Full Attention","created":"2025-03-25","cited_by_count":47},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44},{"id":"2403.09334","title":"Video Editing via Factorized Diffusion Distillation","created":"2024-03-14","cited_by_count":41},{"id":"2412.09645","title":"Evaluation Agent: Efficient and Promptable Evaluation Framework for Visual Generative Models","created":"2024-12-10","cited_by_count":41},{"id":"2312.13834","title":"Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis","created":"2023-12-20","cited_by_count":39},{"id":"2405.14785","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","created":"2024-05-23","cited_by_count":38},{"id":"2412.19761","title":"Generative Video Propagation","created":"2024-12-27","cited_by_count":36},{"id":"2507.14119","title":"NoHumansRequired: Autonomous High-Quality Image Editing Triplet Mining","created":"2025-07-18","cited_by_count":33},{"id":"2411.15260","title":"VIVID-10M: A Dataset and Baseline for Versatile and Interactive Video Local Editing","created":"2024-11-22","cited_by_count":25},{"id":"2506.04213","title":"FullDiT2: Efficient In-Context Conditioning for Video Diffusion Transformers","created":"2025-06-04","cited_by_count":18},{"id":"2506.23361","title":"OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions","created":"2025-06-29","cited_by_count":17},{"id":"2405.18406","title":"RACCooN: A Versatile Instructional Video Editing Framework with Auto-Generated Narratives","created":"2024-05-28","cited_by_count":8},{"id":"2508.06001","title":"KnapFormer: An Online Load Balancer for Efficient Diffusion Transformers Training","created":"2025-08-08","cited_by_count":3}],"next_cursor":null}