Junkang Wu's picture

Junkang Wu

junkang0909

·

https://junkangwu.github.io/

AI & ML interests

LLM alignment

Recent Activity

upvoted a paper 18 days ago

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

upvoted a paper 7 months ago

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

authored a paper 7 months ago

Aligning Multimodal LLM with Human Preference: A Survey

View all activity

Organizations

None yet

upvoted a paper 18 days ago

On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation

Paper • 2603.22117 • Published 21 days ago • 29

upvoted 2 papers 7 months ago

EPO: Entropy-regularized Policy Optimization for LLM Agents Reinforcement Learning

Paper • 2509.22576 • Published Sep 26, 2025 • 137

Quantile Advantage Estimation for Entropy-Safe Reasoning

Paper • 2509.22611 • Published Sep 26, 2025 • 120

upvoted 3 papers about 1 year ago

Aligning Multimodal LLM with Human Preference: A Survey

Paper • 2503.14504 • Published Mar 18, 2025 • 26

Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning

Paper • 2503.07572 • Published Mar 10, 2025 • 48

MM-RLHF: The Next Step Forward in Multimodal LLM Alignment

Paper • 2502.10391 • Published Feb 14, 2025 • 34