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. GeoRelight: Learning Joint Geometrical Relighting and Reconstruction with Flexible Multi-Modal Diffusion Transformers

    Apr 22, 2026Yuxuan Xue, Ruofan Liang, Egor Zakharov +6Image-to-Image TranslationDiffusion Transformer

    Codec Avatars Lab, Meta · University of Tübingen · Max Planck Institute for Informatics, Saarland Informatics Campus

  2. AdaCluster: Adaptive Query-Key Clustering for Sparse Attention in Video Generation

    Apr 20, 2026Haoyue Tan, Shengnan Wang, Yulin Qiao +5Video Diffusion ModelsDiffusion Transformer

    University of Science and Technology of China · Institute of Artificial Intelligence, Hefei Comprehensive National Science Center · 3Independent Researcher +2

  3. LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization

    Apr 20, 2026Yann Bouquet, Alireza Khodamoradi, Sophie Yáng Shen +2Mixed-Precision QuantizationDiffusion Transformer

    Research and Advancement Development Team, Advanced Micro Devices, Inc, USA · Computer Vision Laboratory, Ecole Polytechnique F´ed´erale de Lausanne, Lausanne, Switzerland.

  4. UniCSG: Unified High-Fidelity Content-Constrained Style-Driven Generation via Staged Semantic and Frequency Disentanglement

    Apr 20, 2026Jingwei Yang, Ruoxi Wu, Wei Shen +4Constrained Generative ModelingDiffusion Transformer

    China University of Mining and Technology, Beijing, China · OPPO Artificial Intelligence Center, Beijing, China

  5. Hierarchical Codec Diffusion for Video-to-Speech Generation

    Apr 17, 2026Jiaxin Ye, Gaoxiang Cong, Chenhui Wang +4Audio-Video GenerationDiffusion Transformer

    Fudan University · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +1

  6. OneHOI: Unifying Human-Object Interaction Generation and Editing

    Apr 15, 2026Jiun Tian Hoe, Weipeng Hu, Xudong Jiang +2HOI GenerationDiffusion Transformer

    Nanyang Technological University · Sun Yat-sen University · VinUniversity +1

  7. ASTRA: Enhancing Multi-Subject Generation with Retrieval-Augmented Pose Guidance and Disentangled Position Embedding

    Apr 15, 2026Tianze Xia, Zijian Ning, Zonglin Zhao +1Multi-Subject Image GenerationImage Generation

    Huazhong University of Science and Technology

  8. ADP-DiT: Text-Guided Diffusion Transformer for Brain Image Generation in Alzheimer's Disease Progression

    Apr 15, 2026Juneyong Lee, Geonwoo Baek, Ikbeom JangMedical Image SynthesisConditional Diffusion Models

    Department of Computer Science and Engineering, Hankuk University of Foreign Studies, Seoul, Republic of Korea

  9. Brain-DiT: A Universal Multi-state fMRI Foundation Model with Metadata-Conditioned Pretraining

    Apr 14, 2026Junfeng Xia, Wenhao Ye, Xuanye Pan +3Medical Imaging Foundation ModelsDiffusion Transformer

    Department of Biomedical Engineering, Southern University of Science and Technology, China · School of Biomedical Engineering, Shenzhen University, China

  10. FreqFormer: Hierarchical Frequency-Domain Attention with Adaptive Spectral Routing for Long-Sequence Video Diffusion Transformers

    Apr 14, 2026Haopeng JinDiffusion Model Inference AccelerationDiffusion Transformer

    Beijing University of Posts and Telecommunications

  11. CoSyncDiT: Cognitive Synchronous Diffusion Transformer for Movie Dubbing

    Apr 14, 2026Gaoxiang Cong, Liang Li, Jiaxin Ye +4Audio-Visual AlignmentDiffusion Transformer

    Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Fudan University, Shanghai, China +2

  12. Nucleus-Image: Sparse MoE for Image Generation

    Apr 14, 2026Chandan Akiti, Ajay Modukuri, Murali Nandan Nagarapu +2T2I Diffusion ModelsDiffusion Models

  13. LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching Inference

    Apr 13, 2026Guandong LiFlow MatchingFlow-Based Generative Modeling

    iFLYTEK

  14. Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale

    Apr 13, 2026Dongxu Wei, Qi Xu, Zhiqi Li +63D Scene Generation3D Diffusion Models

    Westlake University · Afari Intelligent Drive · Zhejiang University

  15. Transformers Learn the Optimal DDPM Denoiser for Multi-Token GMMs

    Apr 11, 2026Hongkang Li, Hancheng Min, Rene VidalDiffusion ModelsDiffusion-Based Denoising

    Department of Electrical and Systems Engineering, University of Pennsylvania, Philadelphia, USA · Institute of Natural Sciences & School of Mathematical Sciences, Shanghai Jiao Tong University, Shanghai, China

  16. SHIFT: Steering Hidden Intermediates in Flow Transformers

    Apr 10, 2026Nina Konovalova, Andrey Kuznetsov, Aibek AlanovControllable Image GenerationConcept Erasure

    FusionBrain Lab · HSE University · AXXX

  17. HistDiT: A Structure-Aware Latent Conditional Diffusion Model for High-Fidelity Virtual Staining in Histopathology

    Apr 9, 2026Aasim Bin Saleem, Amr Ahmed, Ardhendu Behera +5Virtual StainingComputational Pathology

    Edge Hill University, Ormskirk, L39 4QP, United Kingdom · University of Nottingham Malaysia, 43500 Semenyih, Malaysia · University of Southampton Malaysia, 79100 Iskandar Puteri, Malaysia +1

  18. Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reuse

    Apr 6, 2026Hao Liu, Ye Huang, Chenghuan Huang +5Diffusion Model CachingDiffusion Model Inference Acceleration

    Sun Yat-sen University, China · Independent Researcher

  19. DiffSparse: Accelerating Diffusion Transformers with Learned Token Sparsity

    Apr 4, 2026Haowei Zhu, Ji Liu, Ziqiong Liu +4Diffusion Model Inference AccelerationDiffusion Models

    Advanced Micro Devices, Inc. · Tsinghua University · BNRist

  20. LumaFlux: Lifting 8-Bit Worlds to HDR Reality with Physically-Guided Diffusion Transformers

    Apr 3, 2026Shreshth Saini, Hakan Gedik, Neil Birkbeck +3HDR ImagingDiffusion Models for Image Restoration

    The University of Texas at Austin · Google, Inc.

  21. Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

    Apr 2, 2026Tin Hadži Veljković, Joshua Rosenthal, Ivor Lončarić +1Diffusion TransformerTransformer

    1UvA-Bosch Delta Lab · University of Amsterdam · 3Ruđer Bošković Institute

  22. SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers

    Apr 2, 2026Xiang Yang, Feifei Li, Mi Zhang +3Safe T2I GenerationDiffusion Transformer

    Fudan University, Shanghai, China · East China University of Science and Technology, Shanghai, China

  23. MotionGrounder: Grounded Multi-Object Motion Transfer via Diffusion Transformer

    Apr 1, 2026Samuel Teodoro, Yun Chen, Agus Gunawan +3Controllable Video GenerationVideo Diffusion Models

    School of Electrical Engineering, Korea Advanced Institute of Science and Technology, Daejeon, South Korea · Adobe Research, San Jose, California · CMLab, Chung-Ang University, Seoul, South Korea

  24. MMFace-DiT: A Dual-Stream Diffusion Transformer for High-Fidelity Multimodal Face Generation

    Mar 30, 2026Bharath Krishnamurthy, Ajita RattaniMultimodal GenerationControllable Image Generation

    University of North Texas, Denton, TX, USA

  25. On-the-fly Repulsion in the Contextual Space for Rich Diversity in Diffusion Transformers

    Mar 30, 2026Omer Dahary, Benaya Koren, Daniel Garibi +1T2I GenerationDiffusion Model Guidance

    Tel Aviv University, Israel · Snap Research, Israel

  26. EdgeDiT: Hardware-Aware Diffusion Transformers for Efficient On-Device Image Generation

    Mar 30, 2026Sravanth Kodavanti, Manjunath Arveti, Sowmya Vajrala +2Diffusion TransformerDiffusion-Based Image Generation

    Samsung Research Institute Bangalore, India

  27. OPRO: Orthogonal Panel-Relative Operators for Panel-Aware In-Context Image Generation

    Mar 29, 2026Sanghyeon Lee, Minwoo Lee, Euijin Shin +3Image GenerationParameter-Efficient Fine-Tuning

    Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea

  28. Spectral-Aware Text-to-Time Series Generation with Billion-Scale Multimodal Meteorological Data

    Mar 28, 2026Shijie ZhangFrequency-Domain Time Series ModelingTime Series Generation

    School of Computer Science and Engineering, Northeastern University, Shenyang, China

  29. EFlow: Fast Few-Step Video Generator Training from Scratch via Efficient Solution Flow

    Mar 28, 2026Dogyun Park, Yanyu Li, Sergey Tulyakov +1Video Diffusion ModelsDiffusion Model Acceleration

    Snap Inc. · Korea University, Seoul, Republic of Korea

  30. MPDiT: Multi-Patch Global-to-Local Transformer Architecture For Efficient Flow Matching and Diffusion Model

    Mar 27, 2026Quan Dao, Dimitris MetaxasDiffusion TransformerDiffusion-Based Image Generation

    Rutgers University