Roman Plaud's picture

1 3 1

Roman Plaud

lecraquito

·

AI & ML interests

None yet

Recent Activity

commented on a paper 5 days ago

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

authored a paper 5 days ago

Revisiting Hierarchical Text Classification: Inference and Metrics

authored a paper 5 days ago

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

View all activity

Organizations

lecraquito's activity

upvoted a paper 6 days ago

Ignore the KL Penalty! Boosting Exploration on Critical Tokens to Enhance RL Fine-Tuning

Paper • 2502.06533 • Published 8 days ago • 16

upvoted a paper 3 months ago

TÜLU 3: Pushing Frontiers in Open Language Model Post-Training

Paper • 2411.15124 • Published Nov 22, 2024 • 59

upvoted a paper 5 months ago

Large Language Models as Markov Chains

Paper • 2410.02724 • Published Oct 3, 2024 • 31