Runzhe Zhan

rzzhan's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

upvoted a paper 7 days ago

Spotlight on Token Perception for Multimodal Reinforcement Learning

Paper • 2510.09285 • Published 11 days ago • 35

upvoted 2 papers 10 days ago

MemMamba: Rethinking Memory Patterns in State Space Model

Paper • 2510.03279 • Published 23 days ago • 68

Agent Learning via Early Experience

Paper • 2510.08558 • Published 12 days ago • 233

upvoted a paper 11 days ago

Diversity-Incentivized Exploration for Versatile Reasoning

Paper • 2509.26209 • Published 21 days ago • 16

upvoted a paper 12 days ago

Native Hybrid Attention for Efficient Sequence Modeling

Paper • 2510.07019 • Published 13 days ago • 16

commented a paper 18 days ago

ExGRPO: Learning to Reason from Experience

Paper • 2510.02245 • Published 19 days ago • 76 •

4

authored a paper 18 days ago

ExGRPO: Learning to Reason from Experience

Paper • 2510.02245 • Published 19 days ago • 76

upvoted a paper 18 days ago

ExGRPO: Learning to Reason from Experience

Paper • 2510.02245 • Published 19 days ago • 76

updated a collection 18 days ago

ExGRPO

Collection

Model collections trained using ExGRPO. • 7 items • Updated 18 days ago • 1

commented a paper 18 days ago

ExGRPO: Learning to Reason from Experience

Paper • 2510.02245 • Published 19 days ago • 76 •

4

updated 3 models 19 days ago

rzzhan/ExGRPO-Qwen2.5-7B-Instruct

8B • Updated 19 days ago • 15

rzzhan/ExGRPO-Llama3.1-8B-Instruct

8B • Updated 19 days ago • 7

rzzhan/ExGRPO-Llama3.1-8B-Zero

8B • Updated 19 days ago • 11

updated a collection 19 days ago

ExGRPO

Collection

Model collections trained using ExGRPO. • 7 items • Updated 18 days ago • 1

published 2 models 19 days ago

rzzhan/ExGRPO-Qwen2.5-7B-Instruct

8B • Updated 19 days ago • 15

rzzhan/ExGRPO-Llama3.1-8B-Instruct

8B • Updated 19 days ago • 7