Zhuoran Jin

jinzhuoran

·

jinzhuoran

AI & ML interests

NLP

Recent Activity

upvoted a paper 1 day ago

Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning

upvoted a paper 1 day ago

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMs

upvoted a paper 15 days ago

The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation

View all activity

Organizations

None yet

Collections 1

Papers 18

arxiv:2606.26027

arxiv:2606.22565

arxiv:2606.12191

arxiv:2603.11896

spaces 1

RWKU

models 4

jinzhuoran/Qwen3-4B-Instruct-16Env

4B • Updated Jan 22 • 8

jinzhuoran/Qwen3-4B-Instruct-32Env

4B • Updated Jan 21 • 5

jinzhuoran/OmniRewardModel

Any-to-Any • 8B • Updated Oct 29, 2025 • 27 • 5

jinzhuoran/OmniRewardModel2

8B • Updated May 19, 2025 • 12

datasets 45

jinzhuoran/MMR-VIP

Viewer • Updated Nov 24, 2025 • 1.68k • 22 • 3

jinzhuoran/OmniRewardData

Viewer • Updated Oct 29, 2025 • 778k • 236 • 2

jinzhuoran/AOKVQA-200

Viewer • Updated May 5, 2025 • 200 • 31

jinzhuoran/MMMU_Pro-200

Viewer • Updated Apr 30, 2025 • 200 • 25

jinzhuoran/MathVista-200

Viewer • Updated Apr 29, 2025 • 200 • 60

jinzhuoran/MathVerse-400

Viewer • Updated Apr 25, 2025 • 400 • 24

jinzhuoran/VisualSimpleQA-200

Viewer • Updated Apr 25, 2025 • 200 • 17

jinzhuoran/MMMU-500

Viewer • Updated Apr 25, 2025 • 500 • 16

jinzhuoran/MathVision-200

Viewer • Updated Apr 25, 2025 • 200 • 44

jinzhuoran/MathVerse-200

Viewer • Updated Apr 25, 2025 • 200 • 20

View 45 datasets