Visual Token Compression

Follow this topic Ask about this topic

Momentum

20 papers in the last four weeks, up 67% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28

Latest papers 184

All topics

SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
Oct 6, 2025Théophane Vallaeys, Jakob Verbeek, Matthieu CordImage Tokenization Image Reconstruction
Meta Fundamental AI Research · Sorbonne University
EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation
Sep 15, 2025Jingyu Xiao, Zhongyi Zhang, Yuxuan Wan +3Efficient Multimodal Inference Code Generation
The Chinese University of Hong Kong, Hong Kong, China · Huazhong University of Science and Technology, Wuhan, China · Singapore Management University, Singapore, Singapore +1
ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance
May 24, 2025Duo Li, Zuhao Yang, Xiaoqin Zhang +2Efficient VLM Inference Large Vision-Language Models
CCDS, NTU, Singapore · CCST, ZJUT, China · Terminus AI Lab, UCAS, China
PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens
Mar 12, 2025Nikolai Körber, Eduard Kromer, Andreas Siebert +3Learned Image Compression Generative Image Compression
Technical University of Munich · University of Applied Sciences Landshut · TU Wien

Oct 6, 2025, cs.CVJ/K move · Enter open · S save

SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization

Théophane Vallaeys, Jakob Verbeek, Matthieu Cord

Meta Fundamental AI Research · Sorbonne University

Image Tokenization Image Reconstruction Pixel-Space Diffusion Models One-Step Generative Modeling Diffusion Model Acceleration Visual Token Compression

Open paper AskPDF arXiv

Tokenizers are a key component of state-of-the-art generative image models, extracting the most important features from the signal while reducing data dimension and redundancy. Most current tokenizers are based on KL-regularized variational autoencoders (KL-VAE), trained with reconstruction, perceptual and adversarial losses. Diffusion decoders have been proposed as a more principled alternative to model the distribution over images conditioned on the latent. However, matching the performance of KL-VAE still requires adversarial losses, as well as a higher decoding time due to iterative sampling. To address these limitations, we introduce a new pixel diffusion decoder architecture for improved scaling and training stability, benefiting from transformer components and GAN-free training. We use distillation to replicate the performance of the diffusion decoder in an efficient single-step decoder. This makes SSDD the first diffusion decoder optimized for single-step reconstruction trained without adversarial losses, reaching higher reconstruction quality and faster sampling than KL-VAE. In particular, SSDD improves reconstruction FID from

0.87

0.46

with

1.4\times

higher throughput and preserve generation quality of DiTs with

3.8\times

faster sampling. As such, SSDD can be used as a drop-in replacement for KL-VAE, and for building higher-quality and faster generative models.

Momentum

Related topics

Latest papers 184

SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization

EfficientUICoder: A Bidirectional Token Compression Framework for Efficient MLLM-Based UI Code Generation

ToDRE: Effective Visual Token Pruning via Token Diversity and Task Relevance

PerCoV2: Ultra-Low Bit-Rate Perceptual Image Compression via Query-Based 1D Multimodal Image Tokens