Roman Plaud's picture

1 4 1

Roman Plaud

lecraquito

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 20 hours ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

commented on a paper 4 months ago

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

authored a paper 4 months ago

Revisiting Hierarchical Text Classification: Inference and Metrics

View all activity

Organizations

lecraquito's activity

upvoted a paper about 20 hours ago

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published 8 days ago • 145

upvoted a paper 4 months ago

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

Paper • 2502.06533 • Published Feb 10 • 18

upvoted a paper 7 months ago

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

Paper • 2411.15124 • Published Nov 22, 2024 • 65

upvoted a paper 8 months ago

Large Language Models as Markov Chains

Paper • 2410.02724 • Published Oct 3, 2024 • 34