{"list":"other","total":103,"rows":[{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"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":"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":"2303.05499","title":"Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection","created":"2023-03-09","cited_by_count":3332},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"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":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2303.04671","title":"Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models","created":"2023-03-08","cited_by_count":668},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2310.05737","title":"Language Model Beats Diffusion -- Tokenizer is Key to Visual Generation","created":"2023-10-09","cited_by_count":640},{"id":"2306.10012","title":"MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing","created":"2023-06-16","cited_by_count":624},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","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":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2409.11340","title":"OmniGen: Unified Image Generation","created":"2024-09-17","cited_by_count":394},{"id":"2404.14396","title":"SEED-X: Multimodal Models with Unified Multi-granularity Comprehension and Generation","created":"2024-04-22","cited_by_count":331},{"id":"2311.10089","title":"Emu Edit: Precise Image Editing via Recognition and Generation Tasks","created":"2023-11-16","cited_by_count":324},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316},{"id":"2306.14435","title":"DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing","created":"2023-06-26","cited_by_count":294},{"id":"2212.05034","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","created":"2022-12-09","cited_by_count":278},{"id":"2407.05282","title":"UltraEdit: Instruction-based Fine-Grained Image Editing at Scale","created":"2024-07-07","cited_by_count":268},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233},{"id":"2401.11708","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs","created":"2024-01-22","cited_by_count":224},{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212},{"id":"2209.14491","title":"Re-Imagen: Retrieval-Augmented Text-to-Image Generator","created":"2022-09-29","cited_by_count":210},{"id":"2304.06939","title":"Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text","created":"2023-04-14","cited_by_count":208},{"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":"2307.02421","title":"DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models","created":"2023-07-05","cited_by_count":195},{"id":"2404.09990","title":"HQ-Edit: A High-Quality Dataset for Instruction-based Image Editing","created":"2024-04-15","cited_by_count":193},{"id":"2305.16807","title":"Negative-prompt Inversion: Fast Image Inversion for Editing with Text-guided Diffusion Models","created":"2023-05-26","cited_by_count":174},{"id":"2312.03594","title":"A Task is Worth One Word: Learning with Task Prompts for High-Quality Versatile Image Inpainting","created":"2023-12-06","cited_by_count":169},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158},{"id":"2504.02160","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","created":"2025-04-02","cited_by_count":154},{"id":"2311.16711","title":"LEDITS++: Limitless Image Editing using Text-to-Image Models","created":"2023-11-28","cited_by_count":148},{"id":"2411.07199","title":"OmniEdit: Building Image Editing Generalist Models Through Specialist Supervision","created":"2024-11-11","cited_by_count":145},{"id":"2503.10589","title":"Long Context Tuning for Video Generation","created":"2025-03-13","cited_by_count":113},{"id":"2412.07774","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","created":"2024-12-10","cited_by_count":102},{"id":"2305.04441","title":"Prompt Tuning Inversion for Text-Driven Image Editing Using Diffusion Models","created":"2023-05-08","cited_by_count":99},{"id":"2308.05095","title":"LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation","created":"2023-08-09","cited_by_count":92},{"id":"2306.05414","title":"Improving Tuning-Free Real Image Editing with Proximal Guidance","created":"2023-06-08","cited_by_count":87},{"id":"2504.08685","title":"Seaweed-7B: Cost-Effective Training of Video Generation Foundation Model","created":"2025-04-11","cited_by_count":82},{"id":"2304.06711","title":"DiffusionRig: Learning Personalized Priors for Facial Appearance Editing","created":"2023-04-13","cited_by_count":75},{"id":"2305.18047","title":"InstructEdit: Improving Automatic Masks for Diffusion-based Image Editing With User Instructions","created":"2023-05-29","cited_by_count":64},{"id":"2311.01410","title":"The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing","created":"2023-11-02","cited_by_count":62},{"id":"2312.10113","title":"Focus on Your Instruction: Fine-grained and Multi-instruction Image Editing by Attention Modulation","created":"2023-12-15","cited_by_count":62},{"id":"2312.16794","title":"ZONE: Zero-Shot Instruction-Guided Local Editing","created":"2023-12-28","cited_by_count":62},{"id":"2503.07703","title":"Seedream 2.0: A Native Chinese-English Bilingual Image Generation Foundation Model","created":"2025-03-10","cited_by_count":62},{"id":"2411.06686","title":"SeedEdit: Align Image Re-Generation to Image Editing","created":"2024-11-11","cited_by_count":61},{"id":"2310.07222","title":"Uni-paint: A Unified Framework for Multimodal Image Inpainting with Pretrained Diffusion Model","created":"2023-10-11","cited_by_count":60},{"id":"2410.00086","title":"ACE: All-round Creator and Editor Following Instructions via Diffusion Transformer","created":"2024-09-30","cited_by_count":56},{"id":"2310.02426","title":"EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods","created":"2023-10-03","cited_by_count":54},{"id":"2404.01050","title":"Drag Your Noise: Interactive Point-based Editing via Diffusion Semantic Propagation","created":"2024-04-01","cited_by_count":51},{"id":"2308.08947","title":"Watch Your Steps: Local Image and Scene Editing by Text Instructions","created":"2023-08-17","cited_by_count":50},{"id":"2307.00522","title":"LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance","created":"2023-07-02","cited_by_count":49},{"id":"2310.13165","title":"CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation","created":"2023-10-19","cited_by_count":41},{"id":"2403.13044","title":"Magic Fixup: Streamlining Photo Editing by Watching Dynamic Videos","created":"2024-03-19","cited_by_count":38},{"id":"2405.14785","title":"EditWorld: Simulating World Dynamics for Instruction-Following Image Editing","created":"2024-05-23","cited_by_count":38},{"id":"2407.03471","title":"Learning Action and Reasoning-Centric Image Editing from Videos and Simulations","created":"2024-07-03","cited_by_count":32},{"id":"2407.18247","title":"RegionDrag: Fast Region-Based Image Editing with Diffusion Models","created":"2024-07-25","cited_by_count":32},{"id":"2409.08857","title":"InstantDrag: Improving Interactivity in Drag-based Image Editing","created":"2024-09-13","cited_by_count":31},{"id":"2310.12149","title":"Object-aware Inversion and Reassembly for Image Editing","created":"2023-10-18","cited_by_count":30},{"id":"2412.17098","title":"DreamOmni: Unified Image Generation and Editing","created":"2024-12-22","cited_by_count":30},{"id":"2506.02368","title":"NextQuill: Causal Preference Modeling for Enhancing LLM Personalization","created":"2025-06-03","cited_by_count":30},{"id":"2502.04370","title":"DreamDPO: Aligning Text-to-3D Generation with Human Preferences via Direct Preference Optimization","created":"2025-02-05","cited_by_count":27},{"id":"2309.10556","title":"Forgedit: Text Guided Image Editing via Learning and Forgetting","created":"2023-09-19","cited_by_count":26},{"id":"2302.11797","title":"Region-Aware Diffusion for Zero-shot Text-driven Image Editing","created":"2023-02-23","cited_by_count":25},{"id":"2406.10462","title":"CoMM: A Coherent Interleaved Image-Text Dataset for Multimodal Understanding and Generation","created":"2024-06-15","cited_by_count":23},{"id":"2305.09979","title":"Self-Training Boosted Multi-Factor Matching Network for Composed Image Retrieval","created":"2023-05-17","cited_by_count":22},{"id":"2312.03584","title":"Context Diffusion: In-Context Aware Image Generation","created":"2023-12-06","cited_by_count":21},{"id":"2312.11396","title":"MAG-Edit: Localized Image Editing in Complex Scenarios via Mask-Based Attention-Adjusted Guidance","created":"2023-12-18","cited_by_count":21},{"id":"2401.07709","title":"Towards Efficient Diffusion-Based Image Editing with Instant Attention Masks","created":"2024-01-15","cited_by_count":16},{"id":"2503.10406","title":"RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models","created":"2025-03-13","cited_by_count":16},{"id":"2412.01824","title":"X-Prompt: Towards Universal In-Context Image Generation in Auto-Regressive Vision Language Foundation Models","created":"2024-12-02","cited_by_count":15},{"id":"2412.05818","title":"SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation","created":"2024-12-08","cited_by_count":15},{"id":"2210.12965","title":"High-Resolution Image Editing via Multi-Stage Blended Diffusion","created":"2022-10-24","cited_by_count":14},{"id":"2405.11190","title":"ReasonPix2Pix: Instruction Reasoning Dataset for Advanced Image Editing","created":"2024-05-18","cited_by_count":14},{"id":"2407.17843","title":"DragText: Rethinking Text Embedding in Point-based Image Editing","created":"2024-07-25","cited_by_count":13},{"id":"2501.08225","title":"FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors","created":"2025-01-14","cited_by_count":13},{"id":"2305.17489","title":"Text-to-image Editing by Image Information Removal","created":"2023-05-27","cited_by_count":12},{"id":"2406.05814","title":"TIGeR: Unifying Text-to-Image Generation and Retrieval with Large Multimodal Models","created":"2024-06-09","cited_by_count":12},{"id":"2309.14934","title":"FEC: Three Finetuning-free Methods to Enhance Consistency for Real Image Editing","created":"2023-09-26","cited_by_count":11}],"next_cursor":"100"}