John's picture

John

johnhan00

·

https://jongwook-han.github.io

AI & ML interests

Pluralistic value alignment

Recent Activity

upvoted a paper 6 days ago

Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States

upvoted a paper 6 days ago

KL for a KL: On-Policy Distillation with Control Variate Baseline

commentedon a paper 25 days ago

ThinkBrake: Efficient Reasoning via Log-Probability Margin Guided Decoding

View all activity

Organizations

liked a dataset 3 months ago

anjalidhabaria/pour_coke_static

Viewer • Updated Jan 31 • 31.4k • 26 • 4

liked a model 7 months ago

nvidia/SO_ARM_Starter_Gr00t

3B • Updated Sep 16, 2025 • 61 • 4

liked a dataset 9 months ago

allenai/WildChat

Viewer • Updated Aug 11, 2025 • 529k • 6.99k • 186

liked a model over 1 year ago

nvidia/Llama-3.1-Nemotron-70B-Instruct-HF

Text Generation • 71B • Updated Apr 13, 2025 • 12k • • 2.07k

liked a model about 2 years ago

meta-llama/Meta-Llama-3-8B

Text Generation • 8B • Updated Sep 27, 2024 • 2.85M • • 6.53k