collaborators

6 papers

cs.AI2026

How to Spend Your Oracle Budget: Practical Guidance for Protein Structure Prediction Models

Aleksandra Kalisz, Jack Simons, Krisztina Sinkovics +4

Foundation models for protein structure prediction remain unreliable on certain targets. External oracles can flag and correct these failures, but biological oracles are expensive,…

cs.LG2026

Force-Aware Neural Tangent Kernels for Scalable and Robust Active Learning of MLIPs

Eszter Varga-Umbrich, Zachary Weller-Davies, Paul Duckworth +3

Active learning for machine-learning interatomic potentials (MLIPs) must address several challenges to be practical: scaling to large candidate pools, leveraging energy-force super…

cs.LG2026

Pretrained Model Representations as Acquisition Signals for Active Learning of MLIPs

Eszter Varga-Umbrich, Shikha Surana, Paul Duckworth +3

Training machine learning interatomic potentials (MLIPs) for reactive chemistry is often bottlenecked by the high cost of quantum chemical labels and the scarcity of transition sta…

stat.ML2026

Sample-Efficient Optimisation over the Outputs of Generative Models

Samuel Willis, Paul Duckworth, Jack Simons +10

Modern generative AI models, such as diffusion and flow matching models, can sample from rich data distributions. However, many applications, especially in science and engineering,…

cs.LG2025

Metalic: Meta-Learning In-Context with Protein Language Models

Jacob Beck, Shikha Surana, Manus McAuliffe +4

Predicting the biophysical and functional properties of proteins is essential for in silico protein design. Machine learning has emerged as a promising technique for such predictio…

cs.LG2025

Overconfident Oracles: Limitations of In Silico Sequence Design Benchmarking

Shikha Surana, Nathan Grinsztajn, Timothy Atkinson +2

Machine learning methods can automate the in silico design of biological sequences, aiming to reduce costs and accelerate medical research. Given the limited access to wet labs, in…