Diffusion Transformer

Also known as DiT

Ask about this topic

Overview

Diffusion Transformers (DiTs) use transformer networks to turn noise into data, typically by repeatedly predicting denoising updates or following a learned flow. Work explores latent- and pixel-space models, conditioning through text, images, geometry, or other modalities, and representation-learning methods that improve generation and downstream perception. To lower the cost of training and inference, researchers use sparse attention, token reduction, caching, quantization, distillation, and hardware-aware designs. A central challenge is balancing speed, memory, and model size against fidelity, temporal or spatial consistency, and reliable performance across tasks and benchmarks.

Latest papers

CardsList

473 papers78 papers in the last four weeks, up 100% on the four weeks before. 0.5% of all new papers.

  1. Read, Allocate, Route: Role-Coupled Tokenization for Pixel-Space Generative Transformers

    Oct 29, 2026Jiongfan Yang, Weichen Fan, Haiwen Diao +2Efficient ViTsTokenization

    Peking University · SenseTime · Nanyang Technological University

  2. UniRA: Unified Representation Alignment and Auto-Encoding for Efficient Diffusion Generation

    Oct 29, 2026An Lanji, Dawei Liu, Jin Li +3Diffusion-Based Image GenerationDiffusion Models

    University of Electronic Science and Technology of China, Chengdu, China.

  3. AB-Attention: Accurate Block Attention for Accelerating Video Diffusion Transformers

    Oct 29, 2026Bin Xu, Mo Zhang, Zhengfeiyang Zhang +6Diffusion Model Inference AccelerationBlock-Sparse Attention

    InfRec · The Chinese University of Hong Kong, Shenzhen · Shandong University +5

  4. SpeeDiff: Scalable Pixel-Anchored End-to-End Latent Diffusion Model

    Oct 26, 2026Bingliang Zhang, Wenda Chu, Yizhuo Li +5Latent Diffusion ModelsDiffusion Transformer

    ByteDance Seed · California Institute of Technology · Meta

  5. Triage: Skip, Skim, or Refine Attention Tiles in Video Diffusion Transformers

    Oct 26, 2026Yeonjae Kim, Omin Kwon, Seong Hoon Seo +1Diffusion Model Inference AccelerationVideo Diffusion Models

    Department of Computer Science and Engineering, Seoul National University, Seoul, Republic of Korea.

  6. Copying As Defense: Protecting Images from Editing By Eliciting Model Copying

    Oct 26, 2026Salma Abdel Magid, Sanghyuk Chun, Eric Slyman +2Adversarial PerturbationsDiffusion-Based Image Editing

    Princeton University · Adobe Research

  7. ImageTTS: Repurposing Pretrained Image Diffusion Transformers for Speech Synthesis

    Oct 26, 2026Hanchen Pei, Shujie Liu, Yayue Deng +4TTS SynthesisZero-Shot TTS

    Electronic Information School, Wuhan University, Wuhan, China · Microsoft Corporation, Redmond, US · The Chinese University of Hong Kong, Hong Kong, China

  8. ToDoPro: Faster and Better Reference-Based Generation: Early Token Reduction via Downsampled Self-Probing

    Oct 26, 2026Caiyi Sun, Yujing Sun, Siu-Ming YiuImage GenerationDiffusion Model Inference Acceleration

    The University of Hong Kong · Nanyang Technological University

  9. HobbyLM: A Sparse Mixture-of-Experts Model Family on a Hobby Budget

    Oct 25, 2026Harish Santhanalakshmi Ganesan, Hariharan M. S., Prabhurajhan RMixture-of-Experts Language ModelsEfficient Language Model Training

  10. Freeze What Is Settled, Cache What Is Smooth: Spatial Freezing Keeps Step Caching in Its Low-Error Regime

    Oct 25, 2026Baiyan Li, Ganxuan YangDiffusion Model Inference AccelerationDiffusion-Based Image Editing

    Lancaster University · Beijing Jiaotong University

  11. How Do DiTs Denoise? An Aggregator-Predictor View of Attention and MLPs

    Oct 21, 2026Gyeonghun Kang, William Xingxu Chen, Xiang ChengDiffusion TransformerDiffusion-Based Denoising

    Department of Statistical Science, Duke University · Department of Computer Science, Duke University · Department of Electrical and Computer Engineering, Duke University

  12. Sparsity Should Be ALLOTted by Output: Training-Free Allocation of Block-Sparse Attention for Video Diffusion Transformers

    Oct 21, 2026Tianze Xia, Xiaoling Zhou, Ruya Lan +3Sparse AttentionDiffusion Model Inference Acceleration

    UCAS · CASIA · KlingAI Research +1

  13. MoDDiT: Simple Token Routing in Diffusion Transformers

    Oct 20, 2026Jarek Liesen, Matthew T. Jackson, Benjamin Ellis +2Diffusion TransformerAdaptive Computation for Diffusion Models

    British Open-ended Learning and Discovery

  14. PixelSR: Pixel-Space Orthogonal Flow Decoupling for Real-World Image Super-Resolution

    Oct 20, 2026Xiang Lv, Kai Zhao, Qiang Wang +3Image Super-ResolutionPixel-Space Diffusion Models

    China University of Petroleum (East China) · Kuaishou Technology · Shenzhen University of Advanced Technology

  15. SpecKCast: Spectral Kalman Forecasting for Diffusion Acceleration

    Oct 19, 2026Javad Rajabi, Hakki Can Karaimer, David B. Lindell +2Diffusion Model Inference AccelerationDiffusion Transformer

    University of Toronto · Vector Institute · AI Center–Toronto, Samsung Electronics

  16. TamedFlow: Trajectory-Aware Distillation for Teacher-Assisted Diffusion Sampling

    Oct 19, 2026Shuaiqi Cheng, Jiahao Zhang, Boyuan Gu +5Diffusion SamplingDiffusion Model Inference Acceleration

    The Hong Kong University of Science and Technology (Guangzhou) · University of Electronic Science and Technology of China · The Hong Kong University of Science and Technology +2

  17. Rethinking the design space of Vanilla Pixel Diffusion Transformers

    Oct 16, 2026Soumik Mukhopadhyay, Long Mai, Abhinav Shrivastava +1Diffusion-Based Image GenerationDiffusion Models

    University of Maryland, College Park · Adobe Research

  18. MOSS-Image Technical Report

    Oct 16, 2026MOSI. AILayout-Guided T2I GenerationText Rendering in T2I Generation

    MOSI Intelligence · SII · Fudan University +1

  19. DIFFLET: A Fast Inference Engine for Diffusion Transformer Models on AWS Trainium

    Oct 16, 2026Bin Ma, Min Yu, Vijay Kodamalla +3Diffusion Model Inference AccelerationDiffusion Model Serving

    Yotta Labs, USA · University of California, Merced, Merced, California, USA.

  20. Sink-Sparse Hybrid Attention for Efficient Inference in T2I/T2V Diffusion Transformers

    Oct 16, 2026Bingxin Xing, Yu Zhang, Jiatong Ding +2Diffusion Model Inference AccelerationSparse Attention

    Xi’an Jiaotong University · Xiamen University · Shanghai Jiao Tong University

  21. OrderFlowDiT: Transport-Regularized Diffusion Transformer for Probabilistic Limit-Order Supply Forecasting

    Oct 15, 2026Jung Hun Phee, Tucker BalchLimit Order Book ForecastingLimit Order Book Modeling

    Georgia Institute of Technology, Atlanta, Georgia, USA · Emory University, Atlanta, Georgia, USA

  22. SoftCache: Adaptive Step Size Caching for Diffusion Transformers

    Oct 15, 2026Shimon Malnick, Nadav Orenstein, Ohad Fried +1Diffusion Model CachingDiffusion Model Inference Acceleration

    Tel Aviv University · Reichman University

  23. Designing Transformers for Continuous Diffusion Language Models

    Oct 15, 2026Weijian Luo, Yujian Chen, Hao Jiang +2Diffusion Language ModelsContinuous Diffusion Language Models

    Dots Studio, Xiaohongshu · Polyadic Research Group · Peking University +2

  24. FocusOPD: Structure-Guided On-Policy Distillation for Diffusion Models

    Oct 15, 2026Xinrui Lin, Shumin Wang, Suqi Song +2Diffusion Model DistillationFeature-Based Knowledge Distillation

    University of Science and Technology of China, Hefei, China · The Hong Kong University of Science and Technology (Guangzhou) · Huawei Noah’s Ark Lab

  25. UltraDiff: Transferring High-Fidelity Priors to Compressed Latent Spaces for High-Resolution Image Generation

    Oct 15, 2026Jingjing Ren, Haitian Zheng, Haoyu Chen +5Latent Diffusion ModelsDiffusion Model Distillation

    The Hong Kong University of Science and Technology (Guangzhou) · Adobe Research

  26. Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced Search

    Oct 15, 2026Yun Dai, Yuyun Chen, Jiarui Wen +3Sparse AttentionDiffusion Model Inference Acceleration

    South China University of Technology

  27. Representation Conditioning for Generation

    Oct 14, 2026Saeed Razavi, Xingjian Leng, Liang ZhengDiffusion-Based Image GenerationDiffusion Transformer

    Australian National University

  28. DeBoneDiT: Depth-Driven Conditional Bridge Diffusion Transformers for Bone Suppression in Chest X-Ray Images

    Oct 14, 2026Yifei Sun, Fenglei Fan, Junhao Jia +4Medical ImagingDiffusion Models for Image Restoration

    Zhejiang University · Hangzhou Dianzi University · City University of Hong Kong +2

  29. MiniDog: Dog-Breed Text-to-image Flow Matching from Pretraining to Fine-Tuning on 4 Consumer GPUs

    Oct 13, 2026Reyhaneh Esmailizadeh, Xingjian Leng, Zhanhao Liang +1T2I GenerationT2I Diffusion Models

  30. Recasting DiT for Extreme Image Compression with Hierarchical Visual Priors

    Oct 13, 2026Yunuo Chen, Jingnan Gao, Bing He +6Learned Image CompressionGenerative Image Compression

    Shanghai Jiao Tong University · University of Sydney