20260705_icml

Members and collaborators of the lab will present the following work at ICML:

• Joint Model and Data Sparsification via the Marginal Likelihood
• Re-evaluating Confidence Remasking in Masked Diffusion Language Models (AdaptFM/SPIGM workshop)
• A Tale of Two Temperatures: Simple, Efficient, and Diverse Sampling from Diffusion Language Models (AdaptFM/SPIGM workshop)
• Uncertainty Estimation for Molecular Diffusion Models (SPIGM workshop)
• Online Safety Monitoring for LLMs (Testing workshop)