Scholar
Roman Plaud
Google Scholar ID: LO3dv_AAAAAJ
PhD Student
Citations & Impact
Citations
12
H-index
2
i10-index
0
Publications
3
Co-authors
6
list available
Publications
Resume (English only)
Academic Achievements
- 1. Paper 'To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers' accepted at ICML 2025.
- 2. Paper 'Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning' accepted at NAACL 2025.
- 3. Paper 'Revisiting Hierarchical Text Classification: Inference and Metrics' accepted at CoNLL 2024.
Research Experience
- Currently a first-year Ph.D. student at Télécom Paris (part of IP Paris) and Onepoint.
Education
- Ph.D. student at Télécom Paris (part of IP Paris) and Onepoint, supervised by Thomas Bonald, Matthieu Labeau, and Antoine Saillenfest; graduated from École des Ponts ParisTech in 2023 with a Master's degree in Mathematics, Vision, and Machine Learning (MVA) from ENS Paris-Saclay.
Background
- Research interests: hierarchical classification, calibration, and optimal decision-making under uncertainty. Graduated from École des Ponts ParisTech and holds a master’s degree in Mathematics, Vision, and Machine Learning (MVA) from ENS Paris-Saclay.
Miscellany
- Feel free to reach out for possible collaborations or questions regarding his research.
