何俊

bdgrahman

3 2

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 10 hours ago

The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation

upvoted a paper about 10 hours ago

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

liked a model about 10 hours ago

Edge0/Audio8-ASR-Infinite

View all activity

Organizations

None yet

models 3

bdgrahman/swin-t-checkpoint

16.6k • Updated 10 days ago • 15

bdgrahman/robotics-vision-language-survey

49.6k • Updated 19 days ago • 20

bdgrahman/efficientformer-checkpoint

16.6k • Updated Aug 27 • 9

datasets 0

None public yet