4 papers
Mat-Pref: Verifiable-Reward Training Improves Compositional Reasoning in Inorganic Materials
Sarrah R. Mikhail Leung, Taehan Kim, Jeongbin Park
Reinforcement learning from verifiable rewards (RLVR) has driven rapid progress in mathematical and code reasoning, but when extended to science, existing benchmarks do not decompo…
Site4Drug: Predicting Drug-Binding Target Sites with an AI Agent
Taehan Kim, Sarrah Rose Mikhail Leung, Bharat Mekala +1
Selecting where to intervene on a protein (i.e., choosing a targetable site) is often a more ambiguous and failure-prone bottleneck than selecting what binds, especially for membra…
SAE-RNA: A Sparse Autoencoder Model for Interpreting RNA Language Model Representations
Taehan Kim, Sangdae Nam
Deep learning, particularly with the advancement of Large Language Models, has transformed biomolecular modeling, with protein language models such as ESM inspiring emerging RNA la…
Interpretable Geometry Sensitivity for Inverse Design of Integrated Photonics
Junho Park, Taehan Kim, Mohammad Ali +1
As an increasingly powerful technique in integrated photonics, inverse design uses optimization algorithms to automatically create compact, high-performance photonic structures, of…