mannaandpoem

manna-ai

·

https://github.com/mannaandpoem

AI & ML interests

None yet

Recent Activity

upvoted a paper about 9 hours ago

TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training

liked a model 2 days ago

upvoted a paper 13 days ago

STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability

View all activity

Organizations

manna-ai 's datasets 5

manna-ai/SWE-Verified_Nano

Viewer • Updated Dec 9, 2024 • 50 • 9

manna-ai/SWE-Verified_Mini

Viewer • Updated Dec 9, 2024 • 100 • 26

manna-ai/SWE-bench_Lite_Unstable

Viewer • Updated Jul 1, 2024 • 49 • 59

manna-ai/SWE-bench_Nano

Viewer • Updated May 28, 2024 • 53 • 81 • 1

manna-ai/SWE-bench_Mini

Viewer • Updated May 28, 2024 • 113 • 126