Junghyun Lee's picture

5

Junghyun Lee

nick-jhlee

https://nick-jhlee.github.io/

AI & ML interests

Bandits, RL Theory, Statistics, Deep Learning Theory, Optimization, etc

Recent Activity

upvoted a paper about 2 months ago

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

upvoted a paper 4 months ago

Flex-Judge: Think Once, Judge Anywhere

upvoted a paper 4 months ago

Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness

View all activity

Organizations

None yet

upvoted a paper about 2 months ago

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Paper • 2507.10524 • Published Jul 14 • 69

upvoted 2 papers 4 months ago

Flex-Judge: Think Once, Judge Anywhere

Paper • 2505.18601 • Published May 24 • 28

Revisiting Multi-Agent Debate as Test-Time Scaling: A Systematic Study of Conditional Effectiveness

Paper • 2505.22960 • Published May 29 • 16

upvoted a paper 5 months ago

Toward Evaluative Thinking: Meta Policy Optimization with Evolving Reward Models

Paper • 2504.20157 • Published Apr 28 • 38

upvoted a paper 6 months ago

DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs

Paper • 2503.07067 • Published Mar 10 • 32