278 citations · 1.5k across the 50 of their papers we have counts for
54 papers
Benchmarking Prompt Optimization of Large Language Models With Chess
Timothée Lesort, Alejandra López de Aberasturi Gómez, Tristan Karch +4
Evaluating large language models becomes increasingly challenging as their capabilities advance: benchmarks can saturate, public test sets risk contamination, and assessing harder…
Future Querying: Can LLMs Serve as Implicit Medical World Models?
Siri Willems, James Butterworth, Lore Goetschalckx +4
Traditional clinical prediction models rely on task-specific pipelines and curated, structured data, which scale poorly and underutilize unstructured text. To address this, we intr…
KernelArc: A Multi-Agent Framework for GPU Kernel Optimization
Joyjit Kundu, Ben Stoffelen, Kaili Wang +2
We present KernelArc, a multi-agent framework for autonomous GPU kernel optimization across heterogeneous workloads. Strategy-specialized agents run in parallel and coordinate thro…
Surfer-H Meets Holo1: Cost-Efficient Web Agent Powered by Open Weights
Mathieu Andreux, Breno Baldas Skuk, Hamza Benchekroun +41
We present Surfer-H, a cost-efficient web agent that integrates Vision-Language Models (VLM) to perform user-defined tasks on the web. We pair it with Holo1, a new open-weight coll…
Offline Learning of Controllable Diverse Behaviors
Mathieu Petitbois, Rémy Portelas, Sylvain Lamprier +1
Imitation Learning (IL) techniques aim to replicate human behaviors in specific tasks. While IL has gained prominence due to its effectiveness and efficiency, traditional methods o…
Hierarchical Subspaces of Policies for Continual Offline Reinforcement Learning
Anthony Kobanda, Rémy Portelas, Odalric-Ambrym Maillard +1
We consider a Continual Reinforcement Learning setup, where a learning agent must continuously adapt to new tasks while retaining previously acquired skill sets, with a focus on th…
Navigation with QPHIL: Quantizing Planner for Hierarchical Implicit Q-Learning
Alexi Canesse, Mathieu Petitbois, Ludovic Denoyer +2
Offline Reinforcement Learning (RL) has emerged as a powerful alternative to imitation learning for behavior modeling in various domains, particularly in complex navigation tasks.…
Efficient Active Imitation Learning with Random Network Distillation
Emilien Biré, Anthony Kobanda, Ludovic Denoyer +1
Developing agents for complex and underspecified tasks, where no clear objective exists, remains challenging but offers many opportunities. This is especially true in video games,…
Policy Diversity for Cooperative Agents
Mingxi Tan, Andong Tian, Ludovic Denoyer
Standard cooperative multi-agent reinforcement learning (MARL) methods aim to find the optimal team cooperative policy to complete a task. However there may exist multiple differen…
Learning Computational Efficient Bots with Costly Features
Anthony Kobanda, Valliappan C. A., Joshua Romoff +1
Deep reinforcement learning (DRL) techniques have become increasingly used in various fields for decision-making processes. However, a challenge that often arises is the trade-off…
Building a Subspace of Policies for Scalable Continual Learning
Jean-Baptiste Gaya, Thang Doan, Lucas Caccia +3
The ability to continuously acquire new knowledge and skills is crucial for autonomous agents. Existing methods are typically based on either fixed-size models that struggle to lea…
Regularized Soft Actor-Critic for Behavior Transfer Learning
Mingxi Tan, Andong Tian, Ludovic Denoyer
Existing imitation learning methods mainly focus on making an agent effectively mimic a demonstrated behavior, but do not address the potential contradiction between the behavior s…
Interactive Query Clarification and Refinement via User Simulation
Pierre Erbacher, Ludovic Denoyer, Laure Soulier
When users initiate search sessions, their queries are often unclear or might lack of context; this resulting in inefficient document ranking. Multiple approaches have been propose…
Temporal Abstractions-Augmented Temporally Contrastive Learning: An Alternative to the Laplacian in RL
Akram Erraqabi, Marlos C. Machado, Mingde Zhao +4
In reinforcement learning, the graph Laplacian has proved to be a valuable tool in the task-agnostic setting, with applications ranging from skill discovery to reward shaping. Rece…
Can I see an Example? Active Learning the Long Tail of Attributes and Relations
Tyler L. Hayes, Maximilian Nickel, Christopher Kanan +2
There has been significant progress in creating machine learning models that identify objects in scenes along with their associated attributes and relationships; however, there is…
State of the Art of User Simulation approaches for conversational information retrieval
Pierre Erbacher, Laure Soulier, Ludovic Denoyer
Conversational Information Retrieval (CIR) is an emerging field of Information Retrieval (IR) at the intersection of interactive IR and dialogue systems for open domain information…
SaLinA: Sequential Learning of Agents
Ludovic Denoyer, Alfredo de la Fuente, Song Duong +3
SaLinA is a simple library that makes implementing complex sequential learning models easy, including reinforcement learning algorithms. It is built as an extension of PyTorch: alg…
Direct then Diffuse: Incremental Unsupervised Skill Discovery for State Covering and Goal Reaching
Pierre-Alexandre Kamienny, Jean Tarbouriech, Sylvain Lamprier +2
Learning meaningful behaviors in the absence of reward is a difficult problem in reinforcement learning. A desirable and challenging unsupervised objective is to learn a set of div…
Learning a subspace of policies for online adaptation in Reinforcement Learning
Jean-Baptiste Gaya, Laure Soulier, Ludovic Denoyer
Deep Reinforcement Learning (RL) is mainly studied in a setting where the training and the testing environments are similar. But in many practical applications, these environments…
On Anytime Learning at Macroscale
Lucas Caccia, Jing Xu, Myle Ott +2
In many practical applications of machine learning data arrives sequentially over time in large chunks. Practitioners have then to decide how to allocate their computational budget…
Efficient Continual Learning with Modular Networks and Task-Driven Priors
Tom Veniat, Ludovic Denoyer, Marc'Aurelio Ranzato
Existing literature in Continual Learning (CL) has focused on overcoming catastrophic forgetting, the inability of the learner to recall how to perform tasks observed in the past.…
Concept Matching for Low-Resource Classification
Federico Errica, Ludovic Denoyer, Bora Edizel +4
We propose a model to tackle classification tasks in the presence of very little training data. To this aim, we approximate the notion of exact match with a theoretically sound mec…
Learning Adaptive Exploration Strategies in Dynamic Environments Through Informed Policy Regularization
Pierre-Alexandre Kamienny, Matteo Pirotta, Alessandro Lazaric +3
We study the problem of learning exploration-exploitation strategies that effectively adapt to dynamic environments, where the task may change over time. While RNN-based policies c…
Learning Dynamic Author Representations with Temporal Language Models
Edouard Delasalles, Sylvain Lamprier, Ludovic Denoyer
Language models are at the heart of numerous works, notably in the text mining and information retrieval communities. These statistical models aim at extracting word distributions,…