architecture · first seen 4 Oct 2026
diffusion transformer
Also: DiT, MM-DiT, latent diffusion transformer, conditional diffusion transformer
Transformer-based diffusion model architecture operating on latent or coordinate tokens for generative modeling.
The diffusion transformer (DiT) replaces the U-Net backbone of diffusion models with a transformer operating on latent or pixel patch tokens, typically conditioned via adaptive layer norm. The sources show it used as a default backbone rather than a new idea: papers on looped DiT cores, pixel-space video diffusion, decoupled encoder-decoder variants, theoretical in-context generation, Thompson sampling with prior-fitted DiTs, amorphous material design, EEG-to-image reconstruction, and sparse inference on mobile SoCs. Code includes open 3B and 5B image models from speridlabs and OpenMOSS and an MLX port for Apple Silicon. The rise reflects broad routine use, not a new concept.
DiT is now the standard backbone for image and video generation and is spreading into scientific and decision-making settings, so variants and efficiency work around it will keep appearing, but the architecture itself has been mainstream since 2023.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 55 on 14 Nov 2026 · 45 mentions in 28 days · 44 independent groups · papers → code · first seen 6 weeks ago · acceleration +1.11
Earliest sources
- Should We Skip Diffusion?Papers · 4 Oct 2026 · Yiping Ji, James Martens, Simon Lucey
- Diffusion Transformers are Provably Optimal In-context GeneratorsPapers · 4 Oct 2026 · Guoji Fu, Tomoya Wakayama, Ryotaro Kawata, Atsushi Nitanda, Wee Sun Lee, Taiji S…
- Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory UpdatePapers · 4 Oct 2026 · Sitian Shen, Jiuming Liu, Mengmeng Liu, Yian Wang, Michael Ying Yang, Francesco…
- LiFT: Loop Flow TransformersPapers · 4 Oct 2026 · Mohammad Mahdi Derakhshani, Pedro M. P. Curvo, Gertjan J. Burghouts, Jan-Willem…
- Controllable Road Marking GenerationPapers · 5 Oct 2026 · Zhiyu Joey Cai, Yufan Zhang, Ruichen Tan, Zengxiang Lei, Satish Ukkusuri
- Level-of-Token DiffusionPapers · 5 Oct 2026 · Kiyohiro Nakayama, Brian Chao, Jan Ackermann, Hansheng Chen, Federico Tombari, L…
Latest sources
- GRAZE: Text-Free Grasp Synthesis for Unseen Objects from Human GazePapers · 16 Nov 2026 · Jeongho Lee, Boeun Kim, Hyung Jin Chang, Jungchan Cho, Sang-Il Choi
- Few-Shot Visual Concept Extraction for Steering Diffusion TransformersPapers · 14 Nov 2026 · Nabyl Quignon, Antitza Dantcheva
- dit.xpu : Taming DiT Sparse Inference on Mobile SoCsPapers · 14 Nov 2026 · Jiayu Chen, Jinye Hu, Maoliang Li, Anqian Cen, Hailong Zou, Zihao Zheng, Xinming…
- Beyond Alignment: Supervising the Generator for EEG-to-Image ReconstructionPapers · 14 Nov 2026 · Sangmin Jo, Wootaek Jeong, Heung-Il Suk
- Role-Separated Diffusion Transformers: Global Rule Isolation and Deterministic Sampling Manifold CompressionPapers · 13 Nov 2026 · Zhiguang Liu, Yi Shang
- JVT: Just Video Transformer makes pixel-space video diffusion simplePapers · 13 Nov 2026 · Jianjun Zhou, Hua Geng, Haoyu Guo
- Graph diffusion transformer for interpretable generation and inverse design of disordered atomic structuresPapers · 13 Nov 2026 · Jiani Hu, Chenyan Wang, Yongkun Yang, Guanyu Hou, Jihaochen Zhang, Lei Liu, Ji C…
- Anionex/h3-image-mlxCode · 10 Nov 2026 · Anionex · 72 stars
- Thompson Sampling using Prior-fitted Diffusion TransformersPapers · 10 Nov 2026 · Sihwa Park, Jingsen Zhu, Vinamr Jain, Sheng-Yen Chou, Alexander Terenin
- MPEG-Diffusion: Mixed-Resolution Video GenerationPapers · 9 Nov 2026 · Dennis Menn, Tianpei Gu, Guande He, Aryan V S, Yanke Song, Nan Liu, Desai Xie, X…
- MG-Cache: Multi-Granularity Caching for Accelerating Diffusion Transformer InferencePapers · 8 Nov 2026 · Zesen Chen, Youxuan Xu, Shigang Li
- CrossLiDAR: Controllable Multi-Sensor LiDAR Sequence GenerationPapers · 8 Nov 2026 · Khanh Nguyen, Thomas Walker, Hichem Telli, Carlos de la Torre-Ortiz, Stefano Fio…