collaborators

5 papers

physics.chem-ph2026

How Well Can Frontier Large Language Models Generate Structures? High Quality Prediction of Molecular Geometries with Help from Fine-Tuning

Joseph M. Cavanagh, Jonathan B. Arnold, Giovanni Battista Alteri +2

The paper explores fine‑tuning large language models to predict equilibrium geometries and conformers of small organic and drug‑like molecules, showing that Z‑matrix representation…

physics.chem-ph2026

SmileyLlama: Modifying Large Language Models for Directed Chemical Space Exploration

Joseph M. Cavanagh, Kunyang Sun, Andrew Gritsevskiy +4

We show that large language model (LLMs) can be transformed via supervised fine-tuning (SFT) of engineered prompts into SmileyLlama for exploring the chemical space of drug molecul…

cs.LG2026

Humanity's Last Exam

Long Phan, Alice Gatti, Ziwen Han +1144

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achi…

cs.LG2025

SynLlama: Generating Synthesizable Molecules and Their Analogs with Large Language Models

Kunyang Sun, Dorian Bagni, Joseph M. Cavanagh +6

Generative machine learning models for exploring chemical space have shown immense promise, but many molecules they generate are too difficult to synthesize, making them impractica…

cs.CR2025

Unelicitable Backdoors in Language Models via Cryptographic Transformer Circuits

Andis Draguns, Andrew Gritsevskiy, Sumeet Ramesh Motwani +3

The rapid proliferation of open-source language models significantly increases the risks of downstream backdoor attacks. These backdoors can introduce dangerous behaviours during m…