14 papers
Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
Ming Gui, Johannes Schusterbauer, Timy Phan +4
We introduce Representation Tokenizer (RepTok), a generative modeling framework that represents an image using a single continuous latent token obtained from self-supervised vision…
SimpleFold: Folding Proteins is Simpler than You Think
Yuyang Wang, Jiarui Lu, Navdeep Jaitly +2
Protein folding models have achieved groundbreaking results typically via a combination of integrating domain knowledge into the architectural blocks and training pipelines. Noneth…
STARFlow-V: End-to-End Video Generative Modeling with Normalizing Flows
Jiatao Gu, Ying Shen, Tianrong Chen +6
Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Y…
TADA: Improved Diffusion Sampling with Training-free Augmented Dynamics
Tianrong Chen, Huangjie Zheng, David Berthelot +3
Diffusion models have demonstrated exceptional capabilities in generating high-fidelity images but typically suffer from inefficient sampling. Many solver designs and noise schedul…
Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows
Ruixiang Zhang, Shuangfei Zhai, Jiatao Gu +6
Autoregressive models have driven remarkable progress in language modeling. Their foundational reliance on discrete tokens, unidirectional context, and single-pass decoding, while…
STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis
Jiatao Gu, Tianrong Chen, David Berthelot +7
We present STARFlow, a scalable generative model based on normalizing flows that achieves strong performance in high-resolution image synthesis. The core of STARFlow is Transformer…