Roman Plaud

lecraquito

·

https://romanplaud.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 19 days ago

Tailoring Strictly Proper Scoring Rules for Downstream Tasks: An Application to Causal Inference

authored a paper 11 months ago

To Each Metric Its Decoding: Post-Hoc Optimal Decision Rules of Probabilistic Hierarchical Classifiers

upvoted a paper about 1 year ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

View all activity

Organizations

upvoted 2 papers about 1 year ago

Absolute Zero: Reinforced Self-play Reasoning with Zero Data

Paper • 2505.03335 • Published May 6, 2025 • 191

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

Paper • 2506.01939 • Published Jun 2, 2025 • 190

upvoted 3 papers over 1 year ago

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

Paper • 2502.06533 • Published Feb 10, 2025 • 17

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

Paper • 2411.15124 • Published Nov 22, 2024 • 69

Large Language Models as Markov Chains

Paper • 2410.02724 • Published Oct 3, 2024 • 33