arxiv:2502.06533
Jean Vassoyan
supertardigrade
AI & ML interests
None yet
Recent Activity
authored
a paper
9 days ago
Ignore the KL Penalty! Boosting Exploration on Critical Tokens to
Enhance RL Fine-Tuning
updated
a model
9 months ago
supertardigrade/2024-05-24_17h08min18
Organizations
None yet