Publications (5)
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
Yutao Xie, Nathaniel Thomas, Nicklas Hansen +3
Search-augmented large language models (LLMs) trained with reinforcement learning (RL) have achieved strong results on open-domain question answering (QA), but training still remai…
Universal Quantum Computation by Scattering in the Fermi-Hubbard Model
Ning Bao, Patrick Hayden, Grant Salton +1
The Hubbard model may be the simplest model of particles interacting on a lattice, but simulation of its dynamics remains beyond the reach of current numerical methods. In this art…
Holographic duality from random tensor networks
Patrick Hayden, Sepehr Nezami, Xiao-Liang Qi +3
Tensor networks provide a natural framework for exploring holographic duality because they obey entanglement area laws. They have been used to construct explicit toy models realizi…
Hierarchical, rotation-equivariant neural networks to select structural models of protein complexes
Stephan Eismann, Raphael J. L. Townshend, Nathaniel Thomas +3
Predicting the structure of multi-protein complexes is a grand challenge in biochemistry, with major implications for basic science and drug discovery. Computational structure pred…
Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
Nathaniel Thomas, Tess Smidt, Steven Kearnes +4
We introduce tensor field neural networks, which are locally equivariant to 3D rotations, translations, and permutations of points at every layer. 3D rotation equivariance removes…