Jinyang Wu's picture

Jinyang Wu

Jinyang23

·

https://orcid.org/my-orcid?orcid=0009-0006-0220-616X

jinyangwu

AI & ML interests

large language models, reasoning, agentic rl

Recent Activity

authored a paper about 15 hours ago

Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles

published a model 1 day ago

Jinyang23/Maestro-4B

updated a model 1 day ago

Jinyang23/Maestro-4B

View all activity

Organizations

None yet

Papers 11

arxiv:2605.22177

arxiv:2602.05843

arxiv:2602.01064

arxiv:2601.20209

models 4

Jinyang23/Maestro-4B

5B • Updated 1 day ago

Jinyang23/Spark-1.5B-ScienceWorld

Reinforcement Learning • 2B • Updated Jan 30 • 3

Jinyang23/Spark-1.5B-WebShop

Reinforcement Learning • 2B • Updated Jan 30 • 1

Jinyang23/Spark-1.5B-ALFWorld

Reinforcement Learning • 2B • Updated Jan 30 • 6

datasets 1

Jinyang23/NoiserBench

Preview • Updated May 31, 2025 • 23 • 2