Romain Deffayet
Scholar

Romain Deffayet

Google Scholar ID: ki7HpkYAAAAJ
Naver Labs Europe
Reinforcement LearningRecommender SystemsUnbiased Learning to Rank
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
131
 
H-index
6
 
i10-index
6
 
Publications
13
 
Co-authors
0
 
Contact
TwitterOpen ↗
Publications
5 items
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
2026
Cited
0
Robust Skills, Brittle Grounding: Diagnosing Restricted Generalization in Vision-Language Action Policies via Multi-Object Picking
2026
Cited
0
RANa: Retrieval-Augmented Navigation
2025
Cited
0
Disentangled Object-Centric Image Representation for Robotic Manipulation
2025
Cited
0
Distributional Reinforcement Learning with Dual Expectile-Quantile Regression
arXiv.org · 2023
Cited
1
Resume
Academic Achievements
  • Publications:
  • - Distributional Reinforcement Learning with Dual Expectile-Quantile Regression
  • - Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset
  • - An Offline Metric for the Debiasedness of Click Models
Research Experience
  • Work Experience: Researcher at Naver Labs Europe.
Background
  • Research Interests: Teaching robots how to do stuff.