TB
Tom Bewley
cs.AIcs.LGcs.CLstat.MLcs.CVcs.ROcs.SDeess.AS
On Valency
published · living versionsW_5txyfx4z·v1 · currentpublished
Preprints & journals
22 papers in the corpus · 2020–2026Shieldstral2607.25857v2 · Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli et al.2026 · 0 citationsarXiv
Robostral Navigate2607.20785v3 · Abdelaziz Bounhar, Abhijeet Somani, Aditi Kabra et al.2026 · 0 citationsarXiv
Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift2605.31250v1 · Salim I. Amoukou, Emanuele Albini, Tom Bewley et al.2026 · 0 citationsarXiv
ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values2604.11200v1 · Tom Bewley, Salim I. Amoukou, Emanuele Albini et al.2026 · 0 citationsarXiv
Voxtral TTS2603.25551v2 · Mistral-AI: Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg et al.2026 · 0 citationsarXiv
Voxtral Realtime2602.11298v3 · Mistral-AI: Alexander H. Liu, Andy Ehrenberg, Andy Lo et al.2026 · 0 citationsarXiv
Ministral 32601.08584v1 · Alexander H. Liu, Kartik Khandelwal, Sandeep Subramanian et al.2026 · 5 citationsarXiv
To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models2510.13290v1 · Anna Hedstrom, Salim I. Amoukou, Tom Bewley et al.2025 · 0 citationsInternational Machine Learning Conference (ICML) 2025
Voxtral2507.13264v1 · Alexander H. Liu, Andy Ehrenberg, Andy Lo et al.2025 · 0 citationsarXiv
Zero-Shot Reinforcement Learning Under Partial Observability2506.15446v1 · Scott Jeen, Tom Bewley, Jonathan M. Cullen2025 · 0 citationsarXiv
Representation Consistency for Accurate and Coherent LLM Answer Aggregation2506.21590v2 · Junqi Jiang, Tom Bewley, Salim I. Amoukou et al.2025 · 0 citationsarXiv
Sequential Harmful Shift Detection Without Labels2412.12910v1 · Salim I. Amoukou, Tom Bewley, Saumitra Mishra et al.2024 · 2 citationsarXiv
Interpreting Language Reward Models via Contrastive Explanations2411.16502v2 · Junqi Jiang, Tom Bewley, Saumitra Mishra et al.2024 · 0 citationsarXiv
Counterfactual Metarules for Local and Global Recourse2405.18875v1 · Tom Bewley, Salim I. Amoukou, Saumitra Mishra et al.2024 · 0 citationsarXiv
Zero-Shot Reinforcement Learning from Low Quality Data2309.15178v3 · Scott Jeen, Tom Bewley, Jonathan M. Cullen2023 · 0 citationsarXiv
Learning Interpretable Models of Aircraft Handling Behaviour by Reinforcement Learning from Human Feedback2305.16924v1 · Tom Bewley, Jonathan Lawry, Arthur Richards2023 · 3 citationsarXiv
Reward Learning with Trees: Methods and Evaluation2210.01007v1 · Tom Bewley, Jonathan Lawry, Arthur Richards et al.2022 · 0 citationsarXiv
Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstraction2201.07749v2 · Tom Bewley, Jonathan Lawry, Arthur Richards2022 · 1 citationarXiv
Interpretable Preference-based Reinforcement Learning with Tree-Structured Reward Functions2112.11230v1 · Tom Bewley, Freddy Lecue2021 · 7 citationsarXiv
TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments2009.04743v2 · Tom Bewley, Jonathan Lawry2020 · 1 citationarXiv
Am I Building a White Box Agent or Interpreting a Black Box Agent?2007.01187v3 · Tom Bewley2020 · 1 citationarXiv
Modelling Agent Policies with Interpretable Imitation Learning2006.11309v1 · Tom Bewley, Jonathan Lawry, Arthur Richards2020 · 3 citationsarXiv
Career total: 27 works. 22 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.