Roman Plaud
3 papers · 2024–2025 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
policy optimization
(1)
kl divergence
(1)
hierarchical text classification
(1)
multi-label classification
(1)
label hierarchy
(1)
reward signal
(1)
hierarchical metric
(1)
reinforcement learning fine-tuning
(1)
token-level exploration
(1)
large language model
(1)
hierarchical classifier
(1)
kl penalty
(1)
critical token
(1)
hierarchical ‘hf₋ scores
(1)
optimal decision rule
(1)
post-hoc decoding
(1)
probabilistic hierarchical classifiers
(1)
underdetermined scenarios
(1)