Agustinus Kristiadi

FlashMD: long-stride, universal prediction of molecular dynamics

Towards Cost-Effective Reward Guided Text Generation

A Critical Look At Tokenwise Reward-Guided Text Generation

Uncertainty-Guided Optimization on Large Language Model Search Trees

A Critical Look At Tokenwise Reward-Guided Text Generation

If Optimizing for general parameters in chemistry is useful, why is it hardly done?

Dimension Debate: Is 3D a Step Too Far for Optimizing Molecules?

On the Disconnect Between Theory and Practice of Overparametrized Neural Networks

Structured Inverse-Free Natural Gradient: Memory-Efficient & Numerically-Stable KFAC for Large Neural Nets