Qianqian Xie's picture

In a Training Loop 🔄

Qianqian Xie

mistletoe111

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 18 hours ago

Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps

upvoted a paper 4 days ago

OProver: A Unified Framework for Agentic Formal Theorem Proving

upvoted a paper 5 days ago

Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution

View all activity

Organizations

Papers 3

arxiv:2604.14683

arxiv:2510.18726

arxiv:2510.17722

models 1

mistletoe111/Simia-Agent-Qwen3-8B-SFT-v1

8B • Updated Mar 23 • 2

datasets 0

None public yet