Michael Sun

Protein Structure Tokenization via Geometric Byte Pair Encoding

Graph Diffusion Transformers are In-Context Molecular Designers

Post Hoc Regression Refinement via Pairwise Rankings

Multimodal Large Language Models for Inverse Molecular Design with Retrosynthetic Planning

Procedural Synthesis of Synthesizable Molecules

Directed Graph Grammars for Sequence-based Learning

Foundation Molecular Grammar: Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages

Two-Stage Pretraining for Molecular Property Prediction in the Wild

Multi-Modal Foundation Models Induce Interpretable Molecular Graph Languages