{"list":"other","total":65,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"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":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2206.01714","title":"Compositional Visual Generation with Composable Diffusion Models","created":"2022-06-03","cited_by_count":624},{"id":"2310.07704","title":"Ferret: Refer and Ground Anything Anywhere at Any Granularity","created":"2023-10-11","cited_by_count":509},{"id":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457},{"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":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2403.04692","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","created":"2024-03-07","cited_by_count":329},{"id":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2307.10816","title":"BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion","created":"2023-07-20","cited_by_count":282},{"id":"2303.17189","title":"LayoutDiffusion: Controllable Diffusion Model for Layout-to-image Generation","created":"2023-03-30","cited_by_count":259},{"id":"2506.18871","title":"OmniGen2: Towards Instruction-Aligned Multimodal Generation","created":"2025-06-23","cited_by_count":253},{"id":"2305.13655","title":"LLM-grounded Diffusion: Enhancing Prompt Understanding of Text-to-Image Diffusion Models with Large Language Models","created":"2023-05-23","cited_by_count":243},{"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":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"2504.11346","title":"Seedream 3.0 Technical Report","created":"2025-04-15","cited_by_count":154},{"id":"2407.05600","title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","created":"2024-07-08","cited_by_count":133},{"id":"2209.08725","title":"Neural Wavelet-domain Diffusion for 3D Shape Generation","created":"2022-09-19","cited_by_count":132},{"id":"2311.16090","title":"Self-correcting LLM-controlled Diffusion Models","created":"2023-11-27","cited_by_count":113},{"id":"2503.10639","title":"GoT: Unleashing Reasoning Capability of Multimodal Large Language Model for Visual Generation and Editing","created":"2025-03-13","cited_by_count":104},{"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":"2006.11807","title":"Improving Image Captioning with Better Use of Captions","created":"2020-06-21","cited_by_count":84},{"id":"2403.16990","title":"Be Yourself: Bounded Attention for Multi-Subject Text-to-Image Generation","created":"2024-03-25","cited_by_count":69},{"id":"2311.17946","title":"DreamSync: Aligning Text-to-Image Generation with Image Understanding Feedback","created":"2023-11-29","cited_by_count":58},{"id":"2310.10640","title":"LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts","created":"2023-10-16","cited_by_count":54},{"id":"2410.14324","title":"HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation","created":"2024-10-18","cited_by_count":41},{"id":"2410.12669","title":"3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation","created":"2024-10-16","cited_by_count":37},{"id":"2401.05675","title":"Parrot: Pareto-optimal Multi-Reward Reinforcement Learning Framework for Text-to-Image Generation","created":"2024-01-11","cited_by_count":36},{"id":"2507.20536","title":"T2I-Copilot: A Training-Free Multi-Agent Text-to-Image System for Enhanced Prompt Interpretation and Interactive Generation","created":"2025-07-28","cited_by_count":33},{"id":"2308.10156","title":"SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation","created":"2023-08-20","cited_by_count":29},{"id":"2412.06771","title":"Proactive Agents for Multi-Turn Text-to-Image Generation Under Uncertainty","created":"2024-12-09","cited_by_count":25},{"id":"2505.02648","title":"MCCD: Multi-Agent Collaboration-based Compositional Diffusion for Complex Text-to-Image Generation","created":"2025-05-05","cited_by_count":23},{"id":"2501.05131","title":"3DIS-FLUX: simple and efficient multi-instance generation with DiT rendering","created":"2025-01-09","cited_by_count":21},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20},{"id":"2509.10704","title":"Maestro: Self-Improving Text-to-Image Generation via Agent Orchestration","created":"2025-09-12","cited_by_count":19},{"id":"2311.01714","title":"EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation","created":"2023-11-03","cited_by_count":16},{"id":"2509.17431","title":"Hierarchical Neural Semantic Representation for 3D Semantic Correspondence","created":"2025-09-22","cited_by_count":14},{"id":"2508.06916","title":"Talk2Image: A Multi-Agent System for Multi-Turn Image Generation and Editing","created":"2025-08-09","cited_by_count":13},{"id":"2306.08226","title":"CLIPXPlore: Coupled CLIP and Shape Spaces for 3D Shape Exploration","created":"2023-06-14","cited_by_count":9},{"id":"2602.18735","title":"LaS-Comp: Zero-shot 3D Completion with Latent-Spatial Consistency","created":"2026-02-21","cited_by_count":9},{"id":"2402.02313","title":"CNS-Edit: 3D Shape Editing via Coupled Neural Shape Optimization","created":"2024-02-04","cited_by_count":8},{"id":"2409.04847","title":"Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation","created":"2024-09-07","cited_by_count":8},{"id":"2502.15972","title":"When Cultures Meet: Multicultural Text-to-Image Generation","created":"2025-02-21","cited_by_count":7},{"id":"2404.18598","title":"Anywhere: A Multi-Agent Framework for User-Guided, Reliable, and Diverse Foreground-Conditioned Image Generation","created":"2024-04-29","cited_by_count":6},{"id":"2602.05362","title":"Imagine a City: CityGenAgent for Procedural 3D City Generation","created":"2026-02-05","cited_by_count":5},{"id":"2602.08198","title":"PEGAsus: 3D Personalization of Geometry and Appearance","created":"2026-02-09","cited_by_count":5},{"id":"2304.06297","title":"ALR-GAN: Adaptive Layout Refinement for Text-to-Image Synthesis","created":"2023-04-13","cited_by_count":4},{"id":"2401.14212","title":"Explicitly Representing Syntax Improves Sentence-to-layout Prediction of Unexpected Situations","created":"2024-01-25","cited_by_count":1}],"next_cursor":null}