4 citations · 12 across the 11 of their papers we have counts for
13 papers
Scaling Online Optimal Transport Minibatches for Flow Matching
Peter Chen, Sergey Levine
A central challenge in scaling flow models is maintaining stability in training and integration. In flow matching, this stability depends critically on how source samples are paire…
Offline Materials Optimization with CliqueFlowmer
Jakub Grudzien Kuba, Benjamin Kurt Miller, Sergey Levine +1
Recent advances in deep learning inspired neural network-based approaches to computational materials discovery (CMD). A plethora of problems in this field involve finding materials…
Bridging the Simulation-to-Experiment Gap with Generative Models using Adversarial Distribution Alignment
Kai Nelson, Tobias Kreiman, Sergey Levine +1
A fundamental challenge in science and engineering is the simulation-to-experiment gap. While we often possess prior knowledge of physical laws, these physical laws can be too diff…
Dynamic Search for Inference-Time Alignment in Diffusion Models
Xiner Li, Masatoshi Uehara, Xingyu Su +5
Diffusion models have shown promising generative capabilities across diverse domains, yet aligning their outputs with desired reward functions remains a challenge, particularly in…
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design
Masatoshi Uehara, Xingyu Su, Yulai Zhao +5
To fully leverage the capabilities of diffusion models, we are often interested in optimizing downstream reward functions during inference. While numerous algorithms for reward-gui…
Inference-Time Alignment in Diffusion Models with Reward-Guided Generation: Tutorial and Review
Masatoshi Uehara, Yulai Zhao, Chenyu Wang +4
This tutorial provides an in-depth guide on inference-time guidance and alignment methods for optimizing downstream reward functions in diffusion models. While diffusion models are…
Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design
Chenyu Wang, Masatoshi Uehara, Yichun He +7
Recent studies have demonstrated the strong empirical performance of diffusion models on discrete sequences across domains from natural language to biological sequence generation.…
Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding
Xiner Li, Yulai Zhao, Chenyu Wang +8
Diffusion models excel at capturing the natural design spaces of images, molecules, DNA, RNA, and protein sequences. However, rather than merely generating designs that are natural…
Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review
Masatoshi Uehara, Yulai Zhao, Tommaso Biancalani +1
This tutorial provides a comprehensive survey of methods for fine-tuning diffusion models to optimize downstream reward functions. While diffusion models are widely known to provid…
Adding Conditional Control to Diffusion Models with Reinforcement Learning
Yulai Zhao, Masatoshi Uehara, Gabriele Scalia +4
Diffusion models are powerful generative models that allow for precise control over the characteristics of the generated samples. While these diffusion models trained on large data…
Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
Masatoshi Uehara, Yulai Zhao, Ehsan Hajiramezanali +5
AI-driven design problems, such as DNA/protein sequence design, are commonly tackled from two angles: generative modeling, which efficiently captures the feasible design space (e.g…
Fine-Tuning of Continuous-Time Diffusion Models as Entropy-Regularized Control
Masatoshi Uehara, Yulai Zhao, Kevin Black +6
Diffusion models excel at capturing complex data distributions, such as those of natural images and proteins. While diffusion models are trained to represent the distribution in th…
Feedback Efficient Online Fine-Tuning of Diffusion Models
Masatoshi Uehara, Yulai Zhao, Kevin Black +6
Diffusion models excel at modeling complex data distributions, including those of images, proteins, and small molecules. However, in many cases, our goal is to model parts of the d…