7 papers
On the Design Space of Discrete Diffusion Online Adaptation for Molecular Optimization
Trevor Chen, Ariel Dai, Jason Yang +8
Molecular optimization often starts from a pretrained generative model that captures a broad prior over valid molecular structures. At test time, however, the goal is not to sample…
End-to-End Autoregressive Image Generation with 1D Semantic Tokenizer
Wenda Chu, Bingliang Zhang, Jiaqi Han +4
Autoregressive image modeling relies on visual tokenizers to compress images into compact latent representations. We design an end-to-end training pipeline that jointly optimizes r…
Discrete Diffusion Trajectory Alignment via Stepwise Decomposition
Jiaqi Han, Austin Wang, Minkai Xu +6
Discrete diffusion models have demonstrated great promise in modeling various sequence data, ranging from human language to biological sequences. Inspired by the success of RL in l…
Steering Generative Models with Experimental Data for Protein Fitness Optimization
Jason Yang, Wenda Chu, Daniel Khalil +4
Protein fitness optimization involves finding a protein sequence that maximizes desired quantitative properties in a combinatorially large design space of possible sequences. Recen…
InverseBench: Benchmarking Plug-and-Play Diffusion Priors for Inverse Problems in Physical Sciences
Hongkai Zheng, Wenda Chu, Bingliang Zhang +9
Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies primarily focus on natural image restor…
Split Gibbs Discrete Diffusion Posterior Sampling
Wenda Chu, Zihui Wu, Yifan Chen +2
We study the problem of posterior sampling in discrete-state spaces using discrete diffusion models. While posterior sampling methods for continuous diffusion models have achieved…