7.8k citations · 9.3k across the 8 of their papers we have counts for
8 papers
TLPO: Token-Level Policy Optimization for Mitigating Language Confusion in Large Language Models
Jinho Choo, JunSeung Lee, Jimyeong Kim +3
Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language, exhibiting a phenomenon known…
Learned Force Fields Are Ready For Ground State Catalyst Discovery
Michael Schaarschmidt, Morgane Riviere, Alex M. Ganose +6
We present evidence that learned density functional theory (``DFT'') force fields are ready for ground state catalyst discovery. Our key finding is that relaxation using forces fro…
Simple GNN Regularisation for 3D Molecular Property Prediction & Beyond
Jonathan Godwin, Michael Schaarschmidt, Alexander Gaunt +5
In this paper we show that simple noise regularisation can be an effective way to address GNN oversmoothing. First we argue that regularisers addressing oversmoothing should both p…
Atomistic graph networks for experimental materials property prediction
Tian Xie, Victor Bapst, Alexander L. Gaunt +5
Machine Learning (ML) has the potential to accelerate discovery of new materials and shed light on useful properties of existing materials. A key difficulty when applying ML in Mat…
Distral: Robust Multitask Reinforcement Learning
Yee Whye Teh, Victor Bapst, Wojciech Marian Czarnecki +5
Most deep reinforcement learning algorithms are data inefficient in complex and rich environments, limiting their applicability to many scenarios. One direction for improving data…
Overcoming catastrophic forgetting in neural networks
James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz +11
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence. Neural networks are not, in general, capable of this and it has been wi…
Progressive Neural Networks
Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins +5
Learning to solve complex sequences of tasks--while both leveraging transfer and avoiding catastrophic forgetting--remains a key obstacle to achieving human-level intelligence. The…
Policy Distillation
Andrei A. Rusu, Sergio Gomez Colmenarejo, Caglar Gulcehre +6
Policies for complex visual tasks have been successfully learned with deep reinforcement learning, using an approach called deep Q-networks (DQN), but relatively large (task-specif…