Generative AI
In-context learning (ICL) approaches typically leverage prompting to condition decoder-only language model generation on reference …
The BrowserGym ecosystem addresses the growing need for efficient evaluation and benchmarking of web agents, particularly those …
Learning generalist embodied agents, able to solve multitudes of tasks in different domains is a long-standing problem. Reinforcement …
Contemporary Large Language Models (LLMs) exhibit a high degree of code generation and comprehension capability. A particularly …
A common and fundamental limitation of Generative AI (GenAI) is its propensity to hallucinate. While large language models (LLM) have …
In model-based optimisation (MBO) we are interested in using machine learning to design candidates that maximise some measure of reward …
Incorporating ethical principles of human-centered AI, such as fostering human autonomy and mindful decision-making, challenges the …
In today’s digitally driven world, dialogue systems play a pivotal role in enhancing user interactions, from customer service to …
In order to safely deploy Large Language Models (LLMs), they must be capable of dynamically adapting their behavior based on their …
We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on …