ZEYU LI

Pr0m1s3zZ

4

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 24 days ago

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

upvoted a paper about 1 month ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

upvoted a paper 5 months ago

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

View all activity

Organizations

upvoted a paper 24 days ago

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Paper • 2610.21601 • Published 25 days ago • 38

upvoted a paper about 1 month ago

Rethinking Cross-Tokenizer On-Policy Distillation: From Alignment Coverage to Supervision Reliability

Paper • 2610.08448 • Published Oct 6 • 34

upvoted a paper 5 months ago

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

Paper • 2605.27068 • Published May 26 • 21

updated a model 9 months ago

Pr0m1s3zZ/Visual_Token_Projection

published a model 9 months ago

Pr0m1s3zZ/Visual_Token_Projection

upvoted a paper about 1 year ago

It Takes Two: Your GRPO Is Secretly DPO

Paper • 2510.00977 • Published Oct 1, 2025 • 32