103 citations · 141 across the 19 of their papers we have counts for
21 papers
A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies
Tu Nguyen, Matthieu Zimmer, Vu Anh Vu +4
A safe action is not necessarily a viable one. A frozen vision-language-action (VLA) policy can favor a locally admissible move that leaves no policy-supported route to safe task c…
The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
Tu Nguyen, Matthieu Zimmer, Rasul Tutunov +2
A recurring pattern in "reasoning without training" is that base LLMs already assign non-trivial probability mass to correct multi-step solutions; the bottleneck is locating these…
Multi-Task GRPO: Reliable LLM Reasoning Across Tasks
Shyam Sundhar Ramesh, Xiaotong Ji, Matthieu Zimmer +5
RL-based post-training with GRPO is widely used to improve large language models on individual reasoning tasks. However, real-world deployment requires reliable performance across…
Subjective Depth and Timescale Transformers: Learning Where and When to Compute
Frederico Wieser, Martin Benfeghoul, Haitham Bou Ammar +2
The rigid, uniform allocation of computation in standard Transformer (TF) architectures can limit their efficiency and scalability, particularly for large-scale models and long seq…
Untangling Component Imbalance in Hybrid Linear Attention Conversion Methods
Martin Benfeghoul, Teresa Delgado, Adnan Oomerjee +3
Transformers' quadratic computational complexity limits their scalability despite remarkable performance. While linear attention reduces this to linear complexity, pre-training suc…
Rethinking Large Language Model Distillation: A Constrained Markov Decision Process Perspective
Matthieu Zimmer, Xiaotong Ji, Tu Nguyen +1
We introduce a novel approach to large language model (LLM) distillation by formulating it as a constrained reinforcement learning problem. While recent work has begun exploring th…
On Almost Surely Safe Alignment of Large Language Models at Inference-Time
Xiaotong Ji, Shyam Sundhar Ramesh, Matthieu Zimmer +3
We introduce a novel inference-time alignment approach for LLMs that aims to generate safe responses almost surely, i.e., with probability approaching one. Our approach models the…
Efficient Reinforcement Learning with Large Language Model Priors
Xue Yan, Yan Song, Xidong Feng +4
In sequential decision-making (SDM) tasks, methods like reinforcement learning (RL) and heuristic search have made notable advances in specific cases. However, they often require e…
Reinforcement Learning for Safe Robot Control using Control Lyapunov Barrier Functions
Desong Du, Shaohang Han, Naiming Qi +3
Reinforcement learning (RL) exhibits impressive performance when managing complicated control tasks for robots. However, its wide application to physical robots is limited by the a…
End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
Alexandre Maraval, Matthieu Zimmer, Antoine Grosnit +1
Meta-Bayesian optimisation (meta-BO) aims to improve the sample efficiency of Bayesian optimisation by leveraging data from related tasks. While previous methods successfully meta-…
Structured Q-learning For Antibody Design
Alexander I. Cowen-Rivers, Philip John Gorinski, Aivar Sootla +5
Optimizing combinatorial structures is core to many real-world problems, such as those encountered in life sciences. For example, one of the crucial steps involved in antibody desi…
Effects of Safety State Augmentation on Safe Exploration
Aivar Sootla, Alexander I. Cowen-Rivers, Jun Wang +1
Safe exploration is a challenging and important problem in model-free reinforcement learning (RL). Often the safety cost is sparse and unknown, which unavoidably leads to constrain…
Sample-Efficient Optimisation with Probabilistic Transformer Surrogates
Alexandre Maraval, Matthieu Zimmer, Antoine Grosnit +3
Faced with problems of increasing complexity, recent research in Bayesian Optimisation (BO) has focused on adapting deep probabilistic models as flexible alternatives to Gaussian P…
Learning Geometric Constraints in Task and Motion Planning
Tianyu Ren, Alexander Imani Cowen-Rivers, Haitham Bou Ammar +1
Searching for bindings of geometric parameters in task and motion planning (TAMP) is a finite-horizon stochastic planning problem with high-dimensional decision spaces. A robot man…
BOiLS: Bayesian Optimisation for Logic Synthesis
Antoine Grosnit, Cedric Malherbe, Rasul Tutunov +3
Optimising the quality-of-results (QoR) of circuits during logic synthesis is a formidable challenge necessitating the exploration of exponentially sized search spaces. While exper…
Viscos Flows: Variational Schur Conditional Sampling With Normalizing Flows
Vincent Moens, Aivar Sootla, Haitham Bou Ammar +1
We present a method for conditional sampling for pre-trained normalizing flows when only part of an observation is available. We derive a lower bound to the conditioning variable l…
Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems
Yaodong Yang, Jun Luo, Ying Wen +5
Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum f…
Efficient Semi-Implicit Variational Inference
Vincent Moens, Hang Ren, Alexandre Maraval +3
In this paper, we propose CI-VI an efficient and scalable solver for semi-implicit variational inference (SIVI). Our method, first, maps SIVI's evidence lower bound (ELBO) to a for…
HEBO Pushing The Limits of Sample-Efficient Hyperparameter Optimisation
Alexander I. Cowen-Rivers, Wenlong Lyu, Rasul Tutunov +8
In this work we rigorously analyse assumptions inherent to black-box optimisation hyper-parameter tuning tasks. Our results on the Bayesmark benchmark indicate that heteroscedastic…
SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving
Ming Zhou, Jun Luo, Julian Villella +34
Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to competently i…
An Exact Distributed Newton Method for Reinforcement Learning
Rasul Tutunov, Haitham Bou-Ammar, Ali Jadbabaie
In this paper, we propose a distributed second- order method for reinforcement learning. Our approach is the fastest in literature so-far as it outperforms state-of-the-art methods…