Michael N

mnoukhov

·

http://mnoukhov.github.io

AI & ML interests

Representation learning for functional language

Recent Activity

upvoted a paper 11 days ago

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

submitted a paper 11 days ago

Learning to Solve Hard Problems in RL for LLMs by Never Giving Up

updated a dataset about 1 month ago

mnoukhov/dolci_think_rl_7b_messages_hybrid_450m_scored

View all activity

Organizations

New activity in allenai/aime-2022-2025 10 months ago

Incorrect dataset name and README description: "allenai/aime-2021-2025" should be "allenai/aime-2022-2025" (same issue in the README).

#2 opened about 1 year ago by

New activity in mistralai/Ministral-3-3B-Base-2512 10 months ago

Incompatibility for Ministral between vllm 0.12.0 and hf transformers 5.0.0

#4 opened 10 months ago by

New activity in facebook/DiT-XL-2-256 over 1 year ago

Confusion on Scheduler

#2 opened over 1 year ago by

commented a paper almost 2 years ago

Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models

Paper • 2410.18252 • Published Oct 23, 2024 • 6 •