activity
20242026
most citedRobust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization

4 citations · 4 across the 2 of their papers we have counts for

collaborators

5 papers

stat.ML2026

Bayesian Invariance Modeling of Multi-Environment Data

Luhuan Wu, Mingzhang Yin, Yixin Wang +2

Invariant prediction [Peters et al., 2016] analyzes feature/outcome data from multiple environments to identify invariant features - those with a stable predictive relationship to…

cs.LG20264 cited

Robust Inference-Time Steering of Protein Diffusion Models via Embedding Optimization

Minhuan Li, Jiequn Han, Pilar Cossio +1

A core challenge in structural biophysics is generating biomolecular conformations that are both physically plausible and consistent with experimental measurements. While sequence-…

stat.CO2025

Reverse Diffusion Sequential Monte Carlo Samplers

Luhuan Wu, Yi Han, Christian A. Naesseth +1

We propose a novel sequential Monte Carlo (SMC) method for sampling from unnormalized target distributions based on a reverse denoising diffusion process. While recent diffusion-ba…

stat.ML2024

Practical and Asymptotically Exact Conditional Sampling in Diffusion Models

Luhuan Wu, Brian L. Trippe, Christian A. Naesseth +2

Diffusion models have been successful on a range of conditional generation tasks including molecular design and text-to-image generation. However, these achievements have primarily…

cs.LG2024

Variational Nearest Neighbor Gaussian Process

Luhuan Wu, Geoff Pleiss, John Cunningham

Variational approximations to Gaussian processes (GPs) typically use a small set of inducing points to form a low-rank approximation to the covariance matrix. In this work, we inst…