{"total":69,"rows":[{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015,"area":"diffusion"},{"id":"2305.10431","title":"FastComposer: Tuning-Free Multi-Subject Image Generation with Localized Attention","created":"2023-05-17","cited_by_count":313,"area":"diffusion"},{"id":"2210.06998","title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","created":"2022-10-13","cited_by_count":168,"area":"diffusion"},{"id":"2212.09462","title":"Latent Diffusion for Language Generation","created":"2022-12-19","cited_by_count":115,"area":"diffusion"},{"id":"2306.14544","title":"A-STAR: Test-time Attention Segregation and Retention for Text-to-image Synthesis","created":"2023-06-26","cited_by_count":78,"area":"diffusion"},{"id":"2211.15462","title":"Investigating Prompt Engineering in Diffusion Models","created":"2022-11-21","cited_by_count":58,"area":"diffusion"},{"id":"2211.04604","title":"StructDiffusion: Language-Guided Creation of Physically-Valid Structures using Unseen Objects","created":"2022-11-08","cited_by_count":50,"area":"diffusion"},{"id":"2312.04549","title":"PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play","created":"2023-12-07","cited_by_count":50,"area":"diffusion"},{"id":"2310.02054","title":"AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model","created":"2023-10-03","cited_by_count":37,"area":"diffusion"},{"id":"2405.13637","title":"Curriculum Direct Preference Optimization for Diffusion and Consistency Models","created":"2024-05-22","cited_by_count":36,"area":"diffusion"},{"id":"2306.00966","title":"The Hidden Language of Diffusion Models","created":"2023-06-01","cited_by_count":34,"area":"diffusion"},{"id":"2410.22366","title":"One-Step is Enough: Sparse Autoencoders for Text-to-Image Diffusion Models","created":"2024-10-28","cited_by_count":33,"area":"diffusion"},{"id":"2310.17680","title":"CodeFusion: A Pre-trained Diffusion Model for Code Generation","created":"2023-10-26","cited_by_count":31,"area":"diffusion"},{"id":"2401.15422","title":"A Survey on Data Augmentation in Large Model Era","created":"2024-01-27","cited_by_count":31,"area":"diffusion"},{"id":"2605.11125","title":"Language Modeling with Hyperspherical Flows","created":"2026-05-11","cited_by_count":22,"area":"diffusion"},{"id":"2308.15459","title":"ParaGuide: Guided Diffusion Paraphrasers for Plug-and-Play Textual Style Transfer","created":"2023-08-29","cited_by_count":18,"area":"diffusion"},{"id":"2404.18928","title":"Stylus: Automatic Adapter Selection for Diffusion Models","created":"2024-04-29","cited_by_count":18,"area":"diffusion"},{"id":"2310.15296","title":"DeTiME: Diffusion-Enhanced Topic Modeling using Encoder-decoder based LLM","created":"2023-10-23","cited_by_count":16,"area":"diffusion"},{"id":"2302.04456","title":"ERNIE-Music: Text-to-Waveform Music Generation with Diffusion Models","created":"2023-02-09","cited_by_count":15,"area":"diffusion"},{"id":"2305.15296","title":"MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation","created":"2023-05-24","cited_by_count":15,"area":"diffusion"},{"id":"2406.12042","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","created":"2024-06-17","cited_by_count":13,"area":"diffusion"},{"id":"2412.01316","title":"Long Video Diffusion Generation with Segmented Cross-Attention and Content-Rich Video Data Curation","created":"2024-12-02","cited_by_count":12,"area":"diffusion"},{"id":"2409.17308","title":"Consistent estimation of generative model representations in the data kernel perspective space","created":"2024-09-25","cited_by_count":10,"area":"diffusion"},{"id":"2308.01472","title":"Reverse Stable Diffusion: What prompt was used to generate this image?","created":"2023-08-02","cited_by_count":7,"area":"diffusion"},{"id":"2405.17934","title":"Proof of Quality: A Costless Paradigm for Trustless Generative AI Model Inference on Blockchains","created":"2024-05-28","cited_by_count":7,"area":"diffusion"},{"id":"2503.16406","title":"VerbDiff: Text-Only Diffusion Models with Enhanced Interaction Awareness","created":"2025-03-20","cited_by_count":7,"area":"diffusion"},{"id":"2509.26391","title":"MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation","created":"2025-09-30","cited_by_count":7,"area":"diffusion"},{"id":"2406.01300","title":"pOps: Photo-Inspired Diffusion Operators","created":"2024-06-03","cited_by_count":6,"area":"diffusion"},{"id":"2311.00949","title":"POS: A Prompts Optimization Suite for Augmenting Text-to-Video Generation","created":"2023-11-02","cited_by_count":4,"area":"diffusion"},{"id":"2409.19952","title":"Image Copy Detection for Diffusion Models","created":"2024-09-30","cited_by_count":4,"area":"diffusion"},{"id":"2506.10047","title":"GenBreak: Red Teaming Text-to-Image Generators Using Large Language Models","created":"2025-06-11","cited_by_count":4,"area":"diffusion"},{"id":"2508.08754","title":"Exploring Palette based Color Guidance in Diffusion Models","created":"2025-08-12","cited_by_count":4,"area":"diffusion"},{"id":"2511.20647","title":"Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization","created":"2025-11-25","cited_by_count":4,"area":"diffusion"},{"id":"2501.05839","title":"Poetry in Pixels: Prompt Tuning for Poem Image Generation via Diffusion Models","created":"2025-01-10","cited_by_count":3,"area":"diffusion"},{"id":"2510.15022","title":"LoRAverse: A Submodular Framework to Retrieve Diverse Adapters for Diffusion Models","created":"2025-10-16","cited_by_count":3,"area":"diffusion"},{"id":"2602.12528","title":"DiffuRank: Effective Document Reranking with Diffusion Language Models","created":"2026-02-13","cited_by_count":3,"area":"diffusion"},{"id":"2410.08207","title":"DICE: Discrete Inversion Enabling Controllable Editing for Multinomial Diffusion and Masked Generative Models","created":"2024-10-10","cited_by_count":2,"area":"diffusion"},{"id":"2508.06837","title":"Towards Effective Prompt Stealing Attack against Text-to-Image Diffusion Models","created":"2025-08-09","cited_by_count":2,"area":"diffusion"},{"id":"2510.06386","title":"Controllable Stylistic Text Generation with Train-Time Attribute-Regularized Diffusion","created":"2025-10-07","cited_by_count":2,"area":"diffusion"},{"id":"2511.22119","title":"PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization","created":"2025-11-27","cited_by_count":2,"area":"diffusion"},{"id":"2512.11348","title":"PhraseVAE and PhraseLDM: Latent Diffusion for Full-Song Multitrack Symbolic Music Generation","created":"2025-12-12","cited_by_count":2,"area":"diffusion"},{"id":"2604.01826","title":"SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers","created":"2026-04-02","cited_by_count":2,"area":"diffusion"},{"id":"2605.31590","title":"TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video Generation","created":"2026-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2606.22370","title":"Towards Error-Free Long Video Generation","created":"2026-06-21","cited_by_count":2,"area":"diffusion"},{"id":"2305.11517","title":"DiffuSIA: A Spiral Interaction Architecture for Encoder-Decoder Text Diffusion","created":"2023-05-19","cited_by_count":1,"area":"diffusion"},{"id":"2406.03215","title":"Searching Priors Makes Text-to-Video Synthesis Better","created":"2024-06-05","cited_by_count":1,"area":"diffusion"},{"id":"2407.11002","title":"MoESD: Mixture of Experts Stable Diffusion to Mitigate Gender Bias","created":"2024-06-25","cited_by_count":1,"area":"diffusion"},{"id":"2502.07090","title":"Generative Distribution Prediction: A Unified Approach to Multimodal Learning","created":"2025-02-10","cited_by_count":1,"area":"diffusion"},{"id":"2503.02595","title":"StageDesigner: Artistic Stage Generation for Scenography via Theater Scripts","created":"2025-03-04","cited_by_count":1,"area":"diffusion"},{"id":"2509.10845","title":"Text2Sign Diffusion: A Generative Approach for Gloss-Free Sign Language Production","created":"2025-09-13","cited_by_count":1,"area":"diffusion"},{"id":"2601.03199","title":"DIP: Dynamic In-Context Planner For Diffusion Language Models","created":"2026-01-06","cited_by_count":1,"area":"diffusion"},{"id":"2602.02600","title":"Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models","created":"2026-02-01","cited_by_count":1,"area":"diffusion"},{"id":"2602.20951","title":"See and Fix the Flaws: Enabling VLMs and Diffusion Models to Comprehend Visual Artifacts via Agentic Data Synthesis","created":"2026-02-24","cited_by_count":1,"area":"diffusion"},{"id":"2605.05503","title":"Chainwash: Multi-Step Rewriting Attacks on Diffusion Language Model Watermarks","created":"2026-05-06","cited_by_count":1,"area":"diffusion"},{"id":"2606.04939","title":"UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning","created":"2026-06-03","cited_by_count":1,"area":"diffusion"},{"id":"2312.15490","title":"Diffusion-EXR: Controllable Review Generation for Explainable Recommendation via Diffusion Models","created":"2023-12-24","cited_by_count":0,"area":"diffusion"},{"id":"2503.10549","title":"Controllable Adversarial Makeup for Privacy via Text-Guided Diffusion","created":"2025-03-13","cited_by_count":0,"area":"diffusion"},{"id":"2506.08185","title":"Agentic Surgical AI: Surgeon Style Fingerprinting and Privacy Risk Quantification via Discrete Diffusion in a Vision-Language-Action Framework","created":"2025-06-09","cited_by_count":0,"area":"diffusion"},{"id":"2507.10861","title":"Visually grounded emotion regulation via diffusion models and user-driven reappraisal","created":"2025-07-14","cited_by_count":0,"area":"diffusion"},{"id":"2511.13312","title":"EL3DD: Extended Latent 3D Diffusion for Language Conditioned Multitask Manipulation","created":"2025-11-17","cited_by_count":0,"area":"diffusion"},{"id":"2511.18104","title":"Consolidating Diffusion-Generated Video Detection with Unified Multimodal Forgery Learning","created":"2025-11-22","cited_by_count":0,"area":"diffusion"},{"id":"2512.08859","title":"Refining Diffusion Models for Motion Synthesis with an Acceleration Loss to Generate Realistic IMU Data","created":"2025-12-09","cited_by_count":0,"area":"diffusion"},{"id":"2601.08095","title":"From Prompts to Deployment: Auto-Curated Domain-Specific Dataset Generation via Diffusion Models","created":"2026-01-13","cited_by_count":0,"area":"diffusion"},{"id":"2603.22509","title":"Sketch2CT: Multimodal Diffusion for Structure-Aware 3D Medical Volume Generation","created":"2026-03-23","cited_by_count":0,"area":"diffusion"},{"id":"2604.09850","title":"Training-Free Object-Background Compositional T2I via Dynamic Spatial Guidance and Multi-Path Pruning","created":"2026-04-10","cited_by_count":0,"area":"diffusion"},{"id":"2604.15009","title":"Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching","created":"2026-04-16","cited_by_count":0,"area":"diffusion"},{"id":"2606.06875","title":"Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows","created":"2026-06-05","cited_by_count":0,"area":"diffusion"},{"id":"2608.05785","title":"Task-Conditional Flow Matching for Balanced Multilingual Text Embedding Adaptation","created":"2026-08-06","cited_by_count":0,"area":"diffusion"},{"id":"2608.16100","title":"TISC: A Text-Driven Image Semantic Communication System for Faithful Reconstruction","created":"2026-08-17","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}