Remi Cadene
Scholar

Remi Cadene

Google Scholar ID: 2n5nHU4AAAAJ
Hugging Face
deep learningroboticsexplainability
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
4,098
 
H-index
20
 
i10-index
21
 
Publications
20
 
Co-authors
0
 
Contact
CVOpen ↗TwitterOpen ↗GitHubOpen ↗
Publications
1 items
LeRobot: An Open-Source Library for End-to-End Robot Learning
2026
Cited
0
Resume (English only)
Academic Achievements
  • Publications:
  • - A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation, NeurIPS (2023)
  • - Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization, NeurIPS (2023)
  • - CRAFT: Concept recursive activation factorization for explainability, CVPR (2023)
  • - Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis, CVPR (2023)
  • - What I cannot predict, I do not understand: A human-centered evaluation framework for explainability methods, NeurIPS (2022)
Research Experience
  • Building next-gen robots at Hugging Face; Previously a research scientist at Tesla, working on Autopilot and Optimus
Education
  • PhD: Sorbonne; Postdoctoral studies: Brown University
Background
  • Scientific interest: Understanding the underlying mechanisms of intelligence; Research focus: Learning human behaviors with neural networks; Working on: Novel architectures, learning approaches, theoretical frameworks, and explainability methods; Other interests: Contributing to open-source projects and reading about neuroscience.
Miscellany
  • Personal interests: Contributing to open-source projects and reading about neuroscience
Co-authors
0 total
Co-authors: 0 (list not available)