Zhuoran Jin

jinzhuoran

·

jinzhuoran

AI & ML interests

NLP

Recent Activity

upvoted a paper 3 days ago

Critique of Agent Model

upvoted a paper 5 days ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

submitted a paper 5 days ago

Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It

View all activity

Organizations

None yet

jinzhuoran 's models 4

jinzhuoran/Qwen3-4B-Instruct-16Env

4B • Updated Jan 22 • 1

jinzhuoran/Qwen3-4B-Instruct-32Env

4B • Updated Jan 21 • 1

jinzhuoran/OmniRewardModel

Any-to-Any • 8B • Updated Oct 29, 2025 • 14 • 5

jinzhuoran/OmniRewardModel2

8B • Updated May 19, 2025 • 5