collaborators

5 papers

cs.LG2026

Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling

Frank Hu, Shriram Chennakesavalu, Zichen Wang +5

Designing viable drug candidates requires searching a combinatorially large and rugged chemical space for molecules that satisfy multiple, often competing, objectives. Large langua…

cs.LG2026

SynLaD: Latent Diffusion for Generating Synthesizable Molecules Conditioned on 3D Pharmacophore Profiles

Miruna Cretu, John Bradshaw, Patricia Suriana +6

We present SynLaD, a latent diffusion framework for small-molecule generation that unifies ligand-based drug design objectives (what to make) with synthetic accessibility (how to m…

cs.LG2026

Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design

Shriram Chennakesavalu, Kirill Shmilovich, Hayley Weir +5

Large Language Models (LLMs) have the potential to accelerate small molecule drug design due to their ability to reason about information from diverse sources and formats. However,…

cs.LG2025

Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learning

Patricia Suriana, Joshua A. Rackers, Ewa M. Nowara +3

Machine learning models for 3D molecular property prediction typically rely on atom-based representations, which may overlook subtle physical information. Electron density maps --…

cs.LG2025

Do we need equivariant models for molecule generation?

Ewa M. Nowara, Joshua Rackers, Patricia Suriana +4

Deep generative models are increasingly used for molecular discovery, with most recent approaches relying on equivariant graph neural networks (GNNs) under the assumption that expl…