← All concepts

diffusion transformer

A diffusion transformer generates data like images by gradually removing noise from random inputs, using a transformer architecture that treats pieces of the data as tokens and pays attention to their relationships. This allows the model to handle complex patterns and create detailed, coherent outputs.

The papers focus on improving efficiency and control. They reduce computation via quantization, token pruning, or frequency-based forecasting, and enhance quality through latent compression or text-guided steering for multimodal generation.

Papers
75
Released code
1
First seen
Sept 2026
Latest
Nov 2026

75 papers in the last two months, against 0 in the two before.

Start here

Three papers to read first, in the order they came out
  1. 1Image generation models can be repurposed for speech synthesis while preserving voice

    ImageTTS repurposes a pretrained image diffusion transformer for speech synthesis using spectrograms as images.

    Oct 2026
  2. 2Driving simulators follow planned paths more faithfully with overhead views

    BirdDreams jointly generates perspective and bird's-eye-view videos to create reactive driving simulations from a single image.

    Nov 2026
  3. 3Few-shot method extracts visual concepts from diffusion model activations for precise editing

    Visual concept directions for image steering can be extracted from Diffusion Transformer activations using only five prompt pairs.

    Nov 2026

Who is working on it

Alibaba Group 7ByteDance Seed 4NVIDIA 3Adobe Research 3The Hong Kong University of Science and Technology 3Google 3

The papers

Most central to this idea first, not most recent.

Concepts are extracted from each paper and reused across the corpus, so this page grows on its own as the desk reads.