35 citations · 243 across the 61 of their papers we have counts for
10 papers · 1 filter
Data-driven Interpretable Hybrid Robot Dynamics
Christopher E. Mower, Rui Zong, Haitham Bou-Ammar
We study data-driven identification of interpretable hybrid robot dynamics, where an analytical rigid-body dynamics model is complemented by a learned residual torque term. Using s…
Model-Based and Sample-Efficient AI-Assisted Math Discovery in Sphere Packing
Rasul Tutunov, Alexandre Maraval, Antoine Grosnit +3
Sphere packing, Hilbert's eighteenth problem, asks for the densest arrangement of congruent spheres in n-dimensional Euclidean space. Although relevant to areas such as cryptograph…
SuRe: Surprise-Driven Prioritised Replay for Continual LLM Learning
Hugo Hazard, Zafeirios Fountas, Martin A. Benfeghoul +3
Continual learning, one's ability to adapt to a sequence of tasks without forgetting previously acquired knowledge, remains a major challenge in machine learning and a key gap betw…
Embodied Arena: A Comprehensive, Unified, and Evolving Evaluation Platform for Embodied AI
Fei Ni, Min Zhang, Pengyi Li +34
Embodied AI development significantly lags behind large foundation models due to three critical challenges: (1) lack of systematic understanding of core capabilities needed for Emb…
Ark: An Open-source Python-based Framework for Robot Learning
Magnus Dierking, Christopher E. Mower, Sarthak Das +10
Robotics has made remarkable hardware strides-from DARPA's Urban and Robotics Challenges to the first humanoid-robot kickboxing tournament-yet commercial autonomy still lags behind…
Bourbaki: Self-Generated and Goal-Conditioned MDPs for Theorem Proving
Matthieu Zimmer, Xiaotong Ji, Rasul Tutunov +3
Reasoning remains a challenging task for large language models (LLMs), especially within the logically constrained environment of automated theorem proving (ATP), due to sparse rew…
A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World
Kaixian Qu, Guowei Lan, René Zurbrügg +4
Large language models (LLMs) have emerged as the dominant paradigm for robotic task planning using natural language instructions. However, trained on general internet data, LLMs ar…
Bottlenecked Transformers: Periodic KV Cache Consolidation for Generalised Reasoning
Adnan Oomerjee, Zafeirios Fountas, Haitham Bou-Ammar +1
Transformer LLMs have been shown to exhibit strong reasoning ability that scales with inference-time compute, most prominently through token-space "thinking" chains of thought. A g…
Al-Khwarizmi: Discovering Physical Laws with Foundation Models
Christopher E. Mower, Haitham Bou-Ammar
Inferring physical laws from data is a central challenge in science and engineering, including but not limited to healthcare, physical sciences, biosciences, social sciences, susta…
Many of Your DPOs are Secretly One: Attempting Unification Through Mutual Information
Rasul Tutnov, Antoine Grosnit, Haitham Bou-Ammar
Post-alignment of large language models (LLMs) is critical in improving their utility, safety, and alignment with human intentions. Direct preference optimisation (DPO) has become…