2 citations · 4 across the 11 of their papers we have counts for
11 papers
TuCo: Measuring the Contribution of Fine-Tuning to Individual Responses of LLMs
Felipe Nuti, Tim Franzmeyer, João Henriques
Past work has studied the effects of fine-tuning on large language models' (LLMs) overall performance on certain tasks. However, a quantitative and systematic method for analyzing…
High Accuracy, Less Talk (HALT): Reliable LLMs through Capability-Aligned Finetuning
Tim Franzmeyer, Archie Sravankumar, Lijuan Liu +6
Large Language Models (LLMs) currently respond to every prompt. However, they can produce incorrect answers when they lack knowledge or capability -- a problem known as hallucinati…
Reinforcement Learning for Quantum Control under Physical Constraints
Jan Ole Ernst, Aniket Chatterjee, Tim Franzmeyer +1
Quantum control is concerned with the realisation of desired dynamics in quantum systems, serving as a linchpin for advancing quantum technologies and fundamental research. Analyti…
Select2Plan: Training-Free ICL-Based Planning through VQA and Memory Retrieval
Davide Buoso, Luke Robinson, Giuseppe Averta +3
This study explores the potential of off-the-shelf Vision-Language Models (VLMs) for high-level robot planning in the context of autonomous navigation. Indeed, while most of existi…
HelloFresh: LLM Evaluations on Streams of Real-World Human Editorial Actions across X Community Notes and Wikipedia edits
Tim Franzmeyer, Aleksandar Shtedritski, Samuel Albanie +3
Benchmarks have been essential for driving progress in machine learning. A better understanding of LLM capabilities on real world tasks is vital for safe development. Designing ade…
Select to Perfect: Imitating desired behavior from large multi-agent data
Tim Franzmeyer, Edith Elkind, Philip Torr +2
AI agents are commonly trained with large datasets of demonstrations of human behavior. However, not all behaviors are equally safe or desirable. Desired characteristics for an AI…
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection
Linas Nasvytis, Kai Sandbrink, Jakob Foerster +2
While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environm…
Extracting Reward Functions from Diffusion Models
Felipe Nuti, Tim Franzmeyer, João F. Henriques
Diffusion models have achieved remarkable results in image generation, and have similarly been used to learn high-performing policies in sequential decision-making tasks. Decision-…
Learn what matters: cross-domain imitation learning with task-relevant embeddings
Tim Franzmeyer, Philip H. S. Torr, João F. Henriques
We study how an autonomous agent learns to perform a task from demonstrations in a different domain, such as a different environment or different agent. Such cross-domain imitation…
Illusory Attacks: Information-Theoretic Detectability Matters in Adversarial Attacks
Tim Franzmeyer, Stephen McAleer, João F. Henriques +4
Autonomous agents deployed in the real world need to be robust against adversarial attacks on sensory inputs. Robustifying agent policies requires anticipating the strongest attack…
Learning Altruistic Behaviours in Reinforcement Learning without External Rewards
Tim Franzmeyer, Mateusz Malinowski, João F. Henriques
Can artificial agents learn to assist others in achieving their goals without knowing what those goals are? Generic reinforcement learning agents could be trained to behave altruis…