Kiều Sơn Tùng

codemaivanngu

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 4 hours ago

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

upvoted a paper about 14 hours ago

DFM Mimir v1: An Open HRM Delivering Frontier Performance at 1B Parameters Using Only Permissible Post-Training Data

upvoted a paper about 14 hours ago

Improving the matrix multiplication exponent with modern optimization and AlphaEvolve

View all activity

Organizations

New activity in ICML-2026-agent-repro/certificate-generator 13 days ago

The first time I have joined a competition on Hugging Face.

#3 opened 13 days ago by

New activity in ICML-2026-agent-repro/challenge 17 days ago

Two evidence-gated reproductions: FA-OPD and SDFT (codemaivanngu)

#33 opened 17 days ago by