장예준

dkim1990

3 4

·

AI & ML interests

Building AI tools for small businesses

Recent Activity

upvoted a paper 9 days ago

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

updated a model 21 days ago

dkim1990/cnn-transformer-experiment

published a model 21 days ago

dkim1990/cnn-transformer-experiment

View all activity

Organizations

None yet

upvoted a paper 9 days ago

Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics

Paper • 2609.38847 • Published 23 days ago • 41

upvoted a paper 29 days ago

Realtime-Venus: A full-duplex interaction system with asynchronous delegation

Paper • 2609.13814 • Published Sep 12 • 161

upvoted a paper about 1 month ago

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published Sep 8 • 82