Yee Whye Teh

StochasTok: Improving Fine-Grained Subword Understanding in LLMs

SigmaDock: Untwisting Molecular Docking with Fragment-Based SE(3) Diffusion

GEM: A Gym for Generalist LLMs

Internalizing World Models via Self-Play Finetuning for Agentic RL

LO-ARMs++: Improving Learning-Order Autoregressive Models for Molecular String Generation

Leave one Expert Out: Robust Uncertainty Quantification via Intrinsic Cross-Validation

MARCOS: Deep Thinking by Markov Chain of Continuous Thoughts

Model Editing is Over: Revealing Its Illusory Success and Fragile Foundation

Rao-Blackwellised Reparameterisation Gradients

SymDiff: Equivariant Diffusion via Stochastic Symmetrisation

Meta-Learning Objectives for Preference Optimization

Learning to Contextualize Web Pages for Enhanced Decision Making by LLM Agents

L3Ms — Lagrange Large Language Models

Learning Loss Landscapes in Preference Optimization

Score-Based Neural Processes