11 citations · 16 across the 7 of their papers we have counts for
7 papers
Understanding Prompt Tuning and In-Context Learning via Meta-Learning
Tim Genewein, Li Kevin Wenliang, Jordi Grau-Moya +3
Prompting is one of the main ways to adapt a pretrained model to target tasks. Besides manually constructing prompts, many prompt optimization methods have been proposed in the lit…
Partition Tree Weighting for Non-Stationary Stochastic Bandits
Joel Veness, Marcus Hutter, Andras Gyorgy +1
This paper considers a generalisation of universal source coding for interaction data, namely data streams that have actions interleaved with observations. Our goal will be to cons…
Why is prompting hard? Understanding prompts on binary sequence predictors
Li Kevin Wenliang, Anian Ruoss, Jordi Grau-Moya +2
Frontier models can be prompted or conditioned to do many tasks, but finding good prompts is not always easy, nor is understanding some performant prompts. We view prompting as fin…
Evaluating Frontier Models for Dangerous Capabilities
Mary Phuong, Matthew Aitchison, Elliot Catt +24
To understand the risks posed by a new AI system, we must understand what it can and cannot do. Building on prior work, we introduce a programme of new "dangerous capability" evalu…
Revisiting Dynamic Evaluation: Online Adaptation for Large Language Models
Amal Rannen-Triki, Jorg Bornschein, Razvan Pascanu +5
We consider the problem of online fine tuning the parameters of a language model at test time, also known as dynamic evaluation. While it is generally known that this approach impr…
Learning Universal Predictors
Jordi Grau-Moya, Tim Genewein, Marcus Hutter +8
Meta-learning has emerged as a powerful approach to train neural networks to learn new tasks quickly from limited data. Broad exposure to different tasks leads to versatile represe…
Distributional Bellman Operators over Mean Embeddings
Li Kevin Wenliang, Grégoire Delétang, Matthew Aitchison +4
We propose a novel algorithmic framework for distributional reinforcement learning, based on learning finite-dimensional mean embeddings of return distributions. We derive several…