Ibragim
ibragim-bad
AI & ML interests
Data for code agents
Recent Activity
upvoted
a
paper
about 9 hours ago
Blockwise Advantage Estimation for Multi-Objective RL with Verifiable Rewards
upvoted
a
paper
7 days ago
IMU-1: Sample-Efficient Pre-training of Small Language Models
new activity
25 days ago
ibragim-bad/github-repos-metadata-40M:Sharing a complementary dataset with repository embeddings