Romain Deffayet

20 papers A* 2A 3Journal 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
Retrieval-Augmented LLM Agents: Learning to Learn from Experience.
CoRR
Thomas Palmeira Ferraz, Romain Deffayet, Vassilina Nikoulina, Hervé Déjean, Stéphane Clinchant
2026 J jnl
Robust Skills, Brittle Grounding: Diagnosing Restricted Generalization in Vision-Language Action Policies via Multi-Object Picking.
CoRR
David Emukpere, Romain Deffayet, Jean-Michel Renders
2025 A conf
Disentangled Object-Centric Image Representation for Robotic Manipulation.
IROS
David Emukpere, Romain Deffayet, Bingbing Wu, Romain Brégier, Michael Niemaz, Jean-Luc Meunier, Denys Proux, Jean-Michel Renders, Seungsu Kim
2025 J jnl
Disentangled Object-Centric Image Representation for Robotic Manipulation.
CoRR
David Emukpere, Romain Deffayet, Bingbing Wu, Romain Brégier, Michael Niemaz, Jean-Luc Meunier, Denys Proux, Jean-Michel Renders, Seungsu Kim
2025 A conf
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression.
UAI
Sami Jullien, Romain Deffayet, Jean-Michel Renders, Paul Groth, Maarten de Rijke
2025 J jnl
RANa: Retrieval-Augmented Navigation.
CoRR
Gianluca Monaci, Rafael S. Rezende, Romain Deffayet, Gabriela Csurka, Guillaume Bono, Hervé Déjean, Stéphane Clinchant, Christian Wolf
2025 J jnl
RANa: Retrieval-Augmented Navigation.
Trans. Mach. Learn. Res.
Gianluca Monaci, Rafael S. Rezende, Romain Deffayet, Gabriela Csurka, Guillaume Bono, Hervé Déjean, Stéphane Clinchant, Christian Wolf
2024 J jnl
SARDINE: Simulator for Automated Recommendation in Dynamic and Interactive Environments.
Trans. Recomm. Syst.
Romain Deffayet, Thibaut Thonet, Dongyoon Hwang, Vassilissa Lehoux, Jean-Michel Renders, Maarten de Rijke
2024 A* conf
Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset.
SIGIR
Philipp Hager, Romain Deffayet, Jean-Michel Renders, Onno Zoeter, Maarten de Rijke
2024 J jnl
Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset.
CoRR
Philipp Hager, Romain Deffayet, Jean-Michel Renders, Onno Zoeter, Maarten de Rijke
2023 A* conf
An Offline Metric for the Debiasedness of Click Models.
SIGIR
Romain Deffayet, Philipp Hager, Jean-Michel Renders, Maarten de Rijke
2023 J jnl
An Offline Metric for the Debiasedness of Click Models.
CoRR
Romain Deffayet, Philipp Hager, Jean-Michel Renders, Maarten de Rijke
2023 J jnl
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression.
CoRR
Sami Jullien, Romain Deffayet, Jean-Michel Renders, Paul Groth, Maarten de Rijke
2023 J jnl
Evaluating the Robustness of Click Models to Policy Distributional Shift.
ACM Trans. Inf. Syst.
Romain Deffayet, Jean-Michel Renders, Maarten de Rijke
2023 A conf
Generative Slate Recommendation with Reinforcement Learning.
WSDM
Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, Maarten de Rijke
2023 J jnl
Generative Slate Recommendation with Reinforcement Learning.
CoRR
Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, Maarten de Rijke
2023 J jnl
Offline Evaluation for Reinforcement Learning-based Recommendation: A Critical Issue and Some Alternatives.
CoRR
Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, Maarten de Rijke
2023 J jnl
Report on the 1st Workshop on Generative Information Retrieval (Gen-IR 2023) at SIGIR 2023.
SIGIR Forum
Gabriel Bénédict, Ruqing Zhang, Donald Metzler, Andrew Yates, Romain Deffayet, Philipp Hager, Sami Jullien
2023 J jnl
SARDINE: A Simulator for Automated Recommendation in Dynamic and Interactive Environments.
CoRR
Romain Deffayet, Thibaut Thonet, Dongyoon Hwang, Vassilissa Lehoux, Jean-Michel Renders, Maarten de Rijke
2022 J jnl
Offline Evaluation for Reinforcement Learning-Based Recommendation: A Critical Issue and Some Alternatives.
SIGIR Forum
Romain Deffayet, Thibaut Thonet, Jean-Michel Renders, Maarten de Rijke