2 citations · 6 across the 11 of their papers we have counts for
15 papers
From Prompts to Posteriors: Can LLM Agents Perform Bayesian Inference in Context?
Linus Filbry, Luckeciano C. Melo, Yarin Gal
Large language models (LLMs) are increasingly applied across the scientific discovery pipeline, from synthesizing literature to generating hypotheses to informing experimental desi…
Richer Bayesian Last Layers with Subsampled NTK Features
Sergio Calvo-Ordoñez, Jonathan Plenk, Richard Bergna +4
Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate uncertainty in neural networks. However, they underestimate epistemic uncertainty bec…
Iterative Deployment Improves Planning Skills in LLMs
Augusto B. Corrêa, Yoav Gelberg, Luckeciano C. Melo +3
We show that iterative deployment of large language models (LLMs), each fine-tuned on data carefully curated by users from the previous models' deployment, can significantly change…
Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning
Gunshi Gupta, Karmesh Yadav, Zsolt Kira +2
To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment…
Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning
Luckeciano C. Melo, Alessandro Abate, Yarin Gal
Reinforcement Learning, particularly through policy gradient methods, has played a central role in enabling reasoning capabilities of Large Language Models. However, the optimizati…
Language Models Change Facts Based on the Way You Talk
Matthew Kearney, Reuben Binns, Yarin Gal
Large language models (LLMs) are increasingly being used in user-facing applications, from providing medical consultations to job interview advice. Recent research suggests that th…
Weighted Conditional Flow Matching
Sergio Calvo-Ordonez, Matthieu Meunier, Alvaro Cartea +3
Conditional flow matching (CFM) has emerged as a powerful framework for training continuous normalizing flows due to its computational efficiency and effectiveness. However, standa…
FindingDory: A Benchmark to Evaluate Memory in Embodied Agents
Karmesh Yadav, Yusuf Ali, Gunshi Gupta +2
Large vision-language models have recently demonstrated impressive performance in planning and control tasks, driving interest in their application to real-world robotics. However,…
Uncertainty-Aware Step-wise Verification with Generative Reward Models
Zihuiwen Ye, Luckeciano Carvalho Melo, Younesse Kaddar +3
Complex multi-step reasoning tasks, such as solving mathematical problems, remain challenging for large language models (LLMs). While outcome supervision is commonly used, process…
Temporal-Difference Variational Continual Learning
Luckeciano C. Melo, Alessandro Abate, Yarin Gal
Machine Learning models in real-world applications must continuously learn new tasks to adapt to shifts in the data-generating distribution. Yet, for Continual Learning (CL), model…
TextCAVs: Debugging vision models using text
Angus Nicolson, Yarin Gal, J. Alison Noble
Concept-based interpretability methods are a popular form of explanation for deep learning models which provide explanations in the form of high-level human interpretable concepts.…
Challenges and Considerations in the Evaluation of Bayesian Causal Discovery
Amir Mohammad Karimi Mamaghan, Panagiotis Tigas, Karl Henrik Johansson +3
Representing uncertainty in causal discovery is a crucial component for experimental design, and more broadly, for safe and reliable causal decision making. Bayesian Causal Discove…
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
Luckeciano C. Melo, Panagiotis Tigas, Alessandro Abate +1
Leveraging human preferences for steering the behavior of Large Language Models (LLMs) has demonstrated notable success in recent years. Nonetheless, data selection and labeling ar…
Explaining Explainability: Recommendations for Effective Use of Concept Activation Vectors
Angus Nicolson, Lisa Schut, J. Alison Noble +1
Concept-based explanations translate the internal representations of deep learning models into a language that humans are familiar with: concepts. One popular method for finding co…
Form follows Function: Text-to-Text Conditional Graph Generation based on Functional Requirements
Peter A. Zachares, Vahan Hovhannisyan, Alan Mosca +1
This work focuses on the novel problem setting of generating graphs conditioned on a description of the graph's functional requirements in a downstream task. We pose the problem as…