Mariia Trofimova
vim-ary
AI & ML interests
NLP
Recent Activity
new activity
5 days ago
Qwen/Qwen3-Coder-30B-A3B-Instruct:SWE-bench Verified Repro
upvoted
a
paper
3 months ago
Training Long-Context, Multi-Turn Software Engineering Agents with
Reinforcement Learning
commented on
a paper
3 months ago
Training Long-Context, Multi-Turn Software Engineering Agents with
Reinforcement Learning