Publications (22)
ButterflyFlow: Building Invertible Layers with Butterfly Matrices
Chenlin Meng, Linqi Zhou, Kristy Choi +2
Normalizing flows model complex probability distributions using maps obtained by composing invertible layers. Special linear layers such as masked and 1x1 convolutions play a key r…
Learning Multi-layer Latent Variable Model via Variational Optimization of Short Run MCMC for Approximate Inference
Erik Nijkamp, Bo Pang, Tian Han +3
This paper studies the fundamental problem of learning deep generative models that consist of multiple layers of latent variables organized in top-down architectures. Such models h…
Personalized Preference Fine-tuning of Diffusion Models
Meihua Dang, Anikait Singh, Linqi Zhou +2
RLHF techniques like DPO can significantly improve the generation quality of text-to-image diffusion models. However, these methods optimize for a single reward that aligns model g…
Three Forms of Stochastic Injection for Improved Distribution-to-Distribution Generative Modeling
Shiye Su, Yuhui Zhang, Linqi Zhou +2
Modeling transformations between arbitrary data distributions is a fundamental scientific challenge, arising in applications like drug discovery and evolutionary simulation. While…
Diffusion Model Alignment Using Direct Preference Optimization
Bram Wallace, Meihua Dang, Rafael Rafailov +7
Large language models (LLMs) are fine-tuned using human comparison data with Reinforcement Learning from Human Feedback (RLHF) methods to make them better aligned with users' prefe…
Curious Replay for Model-based Adaptation
Isaac Kauvar, Chris Doyle, Linqi Zhou +1
Agents must be able to adapt quickly as an environment changes. We find that existing model-based reinforcement learning agents are unable to do this well, in part because of how t…