Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Paper
•
2602.12125
•
Published
•
57
ke mei
kekekeke
AI & ML interests
None yet
Recent Activity
new activity
2 months ago
TIGER-Lab/MMEB-Leaderboard:upload results of WeMM-Embedding-2B and 8B
upvoted
an
article
3 months ago
ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases
Organizations
None yet
upvoted
a
paper
6 days ago
upload results of WeMM-Embedding-2B and 8B
👀
4
3
#86 opened 2 months ago
by
kekekeke
upvoted
an
article
3 months ago
Article
ViDoRe V3: a comprehensive evaluation of retrieval for enterprise use-cases
•
62
Typo in IFM-TTE-7B results for ViDoRe-V2 under Visual Doc
6
#73 opened 4 months ago
by
Hrant
upvoted
a
collection
8 months ago