Linxin Song PRO

linxinso

·

https://linxins97.github.io/

AI & ML interests

LLM,NLP,ML

Recent Activity

upvoted a paper 4 days ago

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

upvoted a paper 6 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

upvoted a paper 10 days ago

Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RL

View all activity

Organizations

linxinso 's papers 12

arxiv:2610.12772

arxiv:2603.10178

arxiv:2602.13949

arxiv:2508.03923

arxiv:2505.13988

arxiv:2504.05520

arxiv:2503.23361

arxiv:2412.08307

arxiv:2412.07012

arxiv:2410.13248

arxiv:2405.19425

arxiv:2402.11359