{"total":35,"rows":[{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305,"area":"diffusion"},{"id":"2205.11495","title":"Flexible Diffusion Modeling of Long Videos","created":"2022-05-23","cited_by_count":294,"area":"diffusion"},{"id":"2402.10885","title":"3D Diffuser Actor: Policy Diffusion with 3D Scene Representations","created":"2024-02-16","cited_by_count":282,"area":"diffusion"},{"id":"2309.03199","title":"Matcha-TTS: A fast TTS architecture with conditional flow matching","created":"2023-09-06","cited_by_count":145,"area":"diffusion"},{"id":"2106.03802","title":"Learning to Efficiently Sample from Diffusion Probabilistic Models","created":"2021-06-07","cited_by_count":129,"area":"diffusion"},{"id":"2209.15611","title":"Protein structure generation via folding diffusion","created":"2022-09-30","cited_by_count":115,"area":"diffusion"},{"id":"2312.02139","title":"DiffiT: Diffusion Vision Transformers for Image Generation","created":"2023-12-04","cited_by_count":106,"area":"diffusion"},{"id":"2304.03283","title":"Diffusion Models as Masked Autoencoders","created":"2023-04-06","cited_by_count":71,"area":"diffusion"},{"id":"2302.05905","title":"Single Motion Diffusion","created":"2023-02-12","cited_by_count":65,"area":"diffusion"},{"id":"2303.05049","title":"Unifying Layout Generation with a Decoupled Diffusion Model","created":"2023-03-09","cited_by_count":41,"area":"diffusion"},{"id":"2412.07776","title":"Video Motion Transfer with Diffusion Transformers","created":"2024-12-10","cited_by_count":39,"area":"diffusion"},{"id":"2406.16260","title":"Video-Infinity: Distributed Long Video Generation","created":"2024-06-24","cited_by_count":30,"area":"diffusion"},{"id":"2311.00613","title":"Controllable Music Production with Diffusion Models and Guidance Gradients","created":"2023-11-01","cited_by_count":29,"area":"diffusion"},{"id":"2212.08034","title":"Generating Realistic Brain MRIs via a Conditional Diffusion Probabilistic Model","created":"2022-12-15","cited_by_count":28,"area":"diffusion"},{"id":"2305.13612","title":"FluentSpeech: Stutter-Oriented Automatic Speech Editing with Context-Aware Diffusion Models","created":"2023-05-23","cited_by_count":23,"area":"diffusion"},{"id":"2303.13472","title":"Promptable Game Models: Text-Guided Game Simulation via Masked Diffusion Models","created":"2023-03-23","cited_by_count":22,"area":"diffusion"},{"id":"2410.13027","title":"Geometric Trajectory Diffusion Models","created":"2024-10-16","cited_by_count":15,"area":"diffusion"},{"id":"2512.05076","title":"BulletTime: Decoupled Control of Time and Camera Pose for Video Generation","created":"2025-12-04","cited_by_count":14,"area":"diffusion"},{"id":"2503.18150","title":"LongDiff: Training-Free Long Video Generation in One Go","created":"2025-03-23","cited_by_count":13,"area":"diffusion"},{"id":"2312.15905","title":"Cross Initialization for Personalized Text-to-Image Generation","created":"2023-12-26","cited_by_count":10,"area":"diffusion"},{"id":"2306.06814","title":"HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models","created":"2023-06-12","cited_by_count":9,"area":"diffusion"},{"id":"2405.00251","title":"Semantically Consistent Video Inpainting with Conditional Diffusion Models","created":"2024-04-30","cited_by_count":8,"area":"diffusion"},{"id":"2411.02322","title":"LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation","created":"2024-11-04","cited_by_count":8,"area":"diffusion"},{"id":"2502.20371","title":"Constrained Generative Modeling with Manually Bridged Diffusion Models","created":"2025-02-27","cited_by_count":8,"area":"diffusion"},{"id":"2406.09263","title":"Generative Inverse Design of Crystal Structures via Diffusion Models with Transformers","created":"2024-06-13","cited_by_count":7,"area":"diffusion"},{"id":"2307.16463","title":"Don't be so negative! Score-based Generative Modeling with Oracle-assisted Guidance","created":"2023-07-31","cited_by_count":6,"area":"diffusion"},{"id":"2305.12628","title":"Duplex Diffusion Models Improve Speech-to-Speech Translation","created":"2023-05-22","cited_by_count":5,"area":"diffusion"},{"id":"2412.04353","title":"ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation","created":"2024-12-05","cited_by_count":4,"area":"diffusion"},{"id":"2505.03063","title":"Variational diffusion transformers for conditional sampling of supernovae spectra","created":"2025-05-05","cited_by_count":1,"area":"diffusion"},{"id":"2603.06664","title":"Accelerating Video Generation Inference with Sequential-Parallel 3D Positional Encoding Using a Global Time Index","created":"2026-03-02","cited_by_count":1,"area":"diffusion"},{"id":"2410.01718","title":"COMUNI: Decomposing Common and Unique Video Signals for Diffusion-based Video Generation","created":"2024-10-02","cited_by_count":0,"area":"diffusion"},{"id":"2506.23254","title":"PixelBoost: Leveraging Brownian Motion for Realistic-Image Super-Resolution","created":"2025-06-29","cited_by_count":0,"area":"diffusion"},{"id":"2512.21890","title":"CrownGen: Patient-customized Crown Generation via Point Diffusion Model","created":"2025-12-26","cited_by_count":0,"area":"diffusion"},{"id":"2603.24270","title":"ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors","created":"2026-03-25","cited_by_count":0,"area":"diffusion"},{"id":"2608.03769","title":"MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language Models","created":"2026-08-04","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}