{"list":"other","total":117,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"1306.0895","title":"Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances","created":"2013-06-04","cited_by_count":2316},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2504.17761","title":"Step1X-Edit: A Practical Framework for General Image Editing","created":"2025-04-24","cited_by_count":429},{"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":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2411.15738","title":"AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea","created":"2024-11-24","cited_by_count":241},{"id":"2312.02133","title":"Style Aligned Image Generation via Shared Attention","created":"2023-12-04","cited_by_count":216},{"id":"2304.00186","title":"Subject-driven Text-to-Image Generation via Apprenticeship Learning","created":"2023-04-01","cited_by_count":212},{"id":"2412.03069","title":"TokenFlow: Unified Image Tokenizer for Multimodal Understanding and Generation","created":"2024-12-04","cited_by_count":202},{"id":"1605.08527","title":"Stochastic Optimization for Large-scale Optimal Transport","created":"2016-05-27","cited_by_count":189},{"id":"2505.00703","title":"T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT","created":"2025-05-01","cited_by_count":166},{"id":"2504.02160","title":"Less-to-More Generalization: Unlocking More Controllability by In-Context Generation","created":"2025-04-02","cited_by_count":154},{"id":"2501.13926","title":"Can We Generate Images with CoT? Let's Verify and Reinforce Image Generation Step by Step","created":"2025-01-23","cited_by_count":131},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"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":"2412.07774","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","created":"2024-12-10","cited_by_count":102},{"id":"2501.02487","title":"ACE++: Instruction-Based Image Creation and Editing via Context-Aware Content Filling","created":"2025-01-05","cited_by_count":95},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89},{"id":"2410.16794","title":"One-Step Diffusion Distillation through Score Implicit Matching","created":"2024-10-22","cited_by_count":71},{"id":"2503.18352","title":"Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models","created":"2025-03-24","cited_by_count":65},{"id":"2504.08736","title":"GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation","created":"2025-04-11","cited_by_count":57},{"id":"2406.02347","title":"Flash Diffusion: Accelerating Any Conditional Diffusion Model for Few Steps Image Generation","created":"2024-06-04","cited_by_count":56},{"id":"2407.00788","title":"InstantStyle-Plus: Style Transfer with Content-Preserving in Text-to-Image Generation","created":"2024-06-30","cited_by_count":53},{"id":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48},{"id":"2411.15466","title":"Large-Scale Text-to-Image Model with Inpainting is a Zero-Shot Subject-Driven Image Generator","created":"2024-11-23","cited_by_count":48},{"id":"2404.14239","title":"MultiBooth: Towards Generating All Your Concepts in an Image from Text","created":"2024-04-22","cited_by_count":45},{"id":"2409.17920","title":"Resolving Multi-Condition Confusion for Finetuning-Free Personalized Image Generation","created":"2024-09-26","cited_by_count":43},{"id":"2502.18364","title":"ART: Anonymous Region Transformer for Variable Multi-Layer Transparent Image Generation","created":"2025-02-25","cited_by_count":37},{"id":"2409.11367","title":"OSV: One Step is Enough for High-Quality Image to Video Generation","created":"2024-09-17","cited_by_count":36},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36},{"id":"2503.01210","title":"Every SAM Drop Counts: Embracing Semantic Priors for Multi-Modality Image Fusion and Beyond","created":"2025-03-03","cited_by_count":35},{"id":"2411.17864","title":"Generative Image Layer Decomposition with Visual Effects","created":"2024-11-26","cited_by_count":34},{"id":"2412.01819","title":"Switti: Designing Scale-Wise Transformers for Text-to-Image Synthesis","created":"2024-12-02","cited_by_count":33},{"id":"2503.12356","title":"Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation","created":"2025-03-16","cited_by_count":33},{"id":"2311.16432","title":"Text-Driven Image Editing via Learnable Regions","created":"2023-11-28","cited_by_count":31},{"id":"2405.12661","title":"EmoEdit: Evoking Emotions through Image Manipulation","created":"2024-05-21","cited_by_count":30},{"id":"2411.09703","title":"MagicQuill: An Intelligent Interactive Image Editing System","created":"2024-11-14","cited_by_count":30},{"id":"2412.01243","title":"Schedule On the Fly: Diffusion Time Prediction for Faster and Better Image Generation","created":"2024-12-02","cited_by_count":30},{"id":"2412.17098","title":"DreamOmni: Unified Image Generation and Editing","created":"2024-12-22","cited_by_count":30},{"id":"2412.04852","title":"SleeperMark: Towards Robust Watermark against Fine-Tuning Text-to-image Diffusion Models","created":"2024-12-06","cited_by_count":29},{"id":"2410.14987","title":"SeaS: Few-shot Industrial Anomaly Image Generation with Separation and Sharing Fine-tuning","created":"2024-10-19","cited_by_count":27},{"id":"2412.02168","title":"Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis","created":"2024-12-03","cited_by_count":26},{"id":"2412.08503","title":"StyleStudio: Text-Driven Style Transfer with Selective Control of Style Elements","created":"2024-12-11","cited_by_count":26},{"id":"2501.05710","title":"EmotiCrafter: Text-to-Emotional-Image Generation based on Valence-Arousal Model","created":"2025-01-10","cited_by_count":26},{"id":"2408.11001","title":"MegaFusion: Extend Diffusion Models towards Higher-resolution Image Generation without Further Tuning","created":"2024-08-20","cited_by_count":25},{"id":"2503.18446","title":"Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models","created":"2025-03-24","cited_by_count":25},{"id":"2503.06132","title":"USP: Unified Self-Supervised Pretraining for Image Generation and Understanding","created":"2025-03-08","cited_by_count":24},{"id":"2406.16476","title":"ResMaster: Mastering High-Resolution Image Generation via Structural and Fine-Grained Guidance","created":"2024-06-24","cited_by_count":22},{"id":"2301.01413","title":"Attribute-Centric Compositional Text-to-Image Generation","created":"2023-01-04","cited_by_count":19},{"id":"2412.03177","title":"PatchDPO: Patch-level DPO for Finetuning-free Personalized Image Generation","created":"2024-12-04","cited_by_count":18},{"id":"2503.10127","title":"PlanGen: Towards Unified Layout Planning and Image Generation in Auto-Regressive Vision Language Models","created":"2025-03-13","cited_by_count":18},{"id":"2411.17323","title":"InsightEdit: Towards Better Instruction Following for Image Editing","created":"2024-11-26","cited_by_count":17},{"id":"2501.01633","title":"ACE: Anti-Editing Concept Erasure in Text-to-Image Models","created":"2025-01-03","cited_by_count":17},{"id":"2405.20216","title":"Boost Your Human Image Generation Model via Direct Preference Optimization","created":"2024-05-30","cited_by_count":16},{"id":"2411.16969","title":"ZoomLDM: Latent Diffusion Model for multi-scale image generation","created":"2024-11-25","cited_by_count":16},{"id":"2412.05848","title":"MotionStone: Decoupled Motion Intensity Modulation with Diffusion Transformer for Image-to-Video Generation","created":"2024-12-08","cited_by_count":16},{"id":"2409.09774","title":"Generalizing Alignment Paradigm of Text-to-Image Generation with Preferences through $f$-divergence Minimization","created":"2024-09-15","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":"2504.00996","title":"TurboFill: Adapting Few-step Text-to-image Model for Fast Image Inpainting","created":"2025-04-01","cited_by_count":15},{"id":"2412.05101","title":"The Silent Assistant: NoiseQuery as Implicit Guidance for Goal-Driven Image Generation","created":"2024-12-06","cited_by_count":14},{"id":"2507.19002","title":"Enhancing Reward Models for High-quality Image Generation: Beyond Text-Image Alignment","created":"2025-07-25","cited_by_count":14},{"id":"2309.03904","title":"Exploring Sparse MoE in GANs for Text-conditioned Image Synthesis","created":"2023-09-07","cited_by_count":13},{"id":"2412.01027","title":"Unleashing In-context Learning of Autoregressive Models for Few-shot Image Manipulation","created":"2024-12-02","cited_by_count":13},{"id":"2501.12910","title":"PreciseCam: Precise Camera Control for Text-to-Image Generation","created":"2025-01-22","cited_by_count":13},{"id":"2503.15197","title":"Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization","created":"2025-03-19","cited_by_count":13},{"id":"2504.02764","title":"Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model","created":"2025-04-03","cited_by_count":13},{"id":"2507.04947","title":"DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer","created":"2025-07-07","cited_by_count":13},{"id":"2411.18552","title":"FAM Diffusion: Frequency and Attention Modulation for High-Resolution Image Generation with Stable Diffusion","created":"2024-11-27","cited_by_count":12},{"id":"2412.12087","title":"Instruction-based Image Manipulation by Watching How Things Move","created":"2024-12-16","cited_by_count":12},{"id":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12},{"id":"2411.17176","title":"ChatGen: Automatic Text-to-Image Generation From FreeStyle Chatting","created":"2024-11-26","cited_by_count":11},{"id":"2503.09669","title":"Silent Branding Attack: Trigger-free Data Poisoning Attack on Text-to-Image Diffusion Models","created":"2025-03-12","cited_by_count":11},{"id":"2507.02358","title":"Hita: Holistic Tokenizer for Autoregressive Image Generation","created":"2025-07-03","cited_by_count":11},{"id":"2508.07647","title":"LaRender: Training-Free Occlusion Control in Image Generation via Latent Rendering","created":"2025-08-11","cited_by_count":11},{"id":"2501.12976","title":"LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation","created":"2025-01-22","cited_by_count":10},{"id":"2503.06956","title":"LatexBlend: Scaling Multi-concept Customized Generation with Latent Textual Blending","created":"2025-03-10","cited_by_count":10},{"id":"2503.16944","title":"HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis","created":"2025-03-21","cited_by_count":10},{"id":"2507.21391","title":"Multimodal LLMs as Customized Reward Models for Text-to-Image Generation","created":"2025-07-28","cited_by_count":10},{"id":"2508.00728","title":"YOLO-Count: Differentiable Object Counting for Text-to-Image Generation","created":"2025-08-01","cited_by_count":10},{"id":"2404.03632","title":"Reference-Based 3D-Aware Image Editing with Triplanes","created":"2024-04-04","cited_by_count":9},{"id":"2501.06481","title":"Focus-N-Fix: Region-Aware Fine-Tuning for Text-to-Image Generation","created":"2025-01-11","cited_by_count":9},{"id":"2503.18406","title":"Instruct-CLIP: Improving Instruction-Guided Image Editing with Automated Data Refinement Using Contrastive Learning","created":"2025-03-24","cited_by_count":9},{"id":"2504.06675","title":"Probability Density Geodesics in Image Diffusion Latent Space","created":"2025-04-09","cited_by_count":9},{"id":"2504.09454","title":"D$^2$iT: Dynamic Diffusion Transformer for Accurate Image Generation","created":"2025-04-13","cited_by_count":9},{"id":"2411.18159","title":"Type-R: Automatically Retouching Typos for Text-to-Image Generation","created":"2024-11-27","cited_by_count":7},{"id":"2412.05538","title":"Not Just Text: Uncovering Vision Modality Typographic Threats in Image Generation Models","created":"2024-12-07","cited_by_count":7},{"id":"2503.10112","title":"MoEdit: On Learning Quantity Perception for Multi-object Image Editing","created":"2025-03-13","cited_by_count":7},{"id":"2503.10358","title":"ConceptGuard: Continual Personalized Text-to-Image Generation with Forgetting and Confusion Mitigation","created":"2025-03-13","cited_by_count":7},{"id":"2505.00502","title":"Towards Scalable Human-aligned Benchmark for Text-guided Image Editing","created":"2025-05-01","cited_by_count":7},{"id":"2411.17786","title":"DreamCache: Finetuning-Free Lightweight Personalized Image Generation via Feature Caching","created":"2024-11-26","cited_by_count":6},{"id":"2503.15283","title":"TF-TI2I: Training-Free Text-and-Image-to-Image Generation via Multi-Modal Implicit-Context Learning in Text-to-Image Models","created":"2025-03-19","cited_by_count":6}],"next_cursor":"100"}