4 papers · 1 filter
WaiT for the Signal: Simple Frequency-Aware Flow-Matching
Krunoslav Lehman Pavasovic, Théophane Vallaeys, Stéphane Mallat +4
As image generation models scale to ever higher resolutions, global coherence, local detail, and texture fidelity become critical axes for generation quality. However, standard flo…
SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization
Théophane Vallaeys, Jakob Verbeek, Matthieu Cord
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. Mos…
Beyond Language Modeling: An Exploration of Multimodal Pretraining
Shengbang Tong, David Fan, John Nguyen +18
The visual world offers a critical axis for advancing foundation models beyond language. Despite growing interest in this direction, the design space for native multimodal models r…
VUGEN: Visual Understanding priors for GENeration
Xiangyi Chen, Théophane Vallaeys, Maha Elbayad +2
Recent advances in Vision-Language Models (VLMs) have enabled unified understanding across text and images, yet equipping these models with robust image generation capabilities rem…