wenlong deng's picture

wenlong deng

dwenlong

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 4 days ago

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

submitted a paper 4 days ago

Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

upvoted a paper 22 days ago

Privileged Information Distillation for Language Models

View all activity

Organizations

Papers 6

arxiv:2603.12634

arxiv:2602.00344

arxiv:2512.04220

arxiv:2510.03669

models 3

dwenlong/skewr-entropy

2B • Updated Jan 17

dwenlong/skewr-entropy-05

2B • Updated Jan 17 • 1

dwenlong/skewr-entropy-01

2B • Updated Jan 17 • 4

datasets 0

None public yet