OPID
Jinyang Wu
Jinyang23
AI & ML interests
large language models, reasoning, agentic rl
Recent Activity
authored a paper about 14 hours ago
TACO: Tool-Augmented Credit Optimization for Agentic Tool Use updated a collection about 20 hours ago
OPID updated a collection about 20 hours ago
OPIDOrganizations
None yet
Spark
-
Jinyang23/Spark-1.5B-WebShop
Reinforcement Learning • 2B • Updated • 2 • 1 -
Jinyang23/Spark-1.5B-ALFWorld
Reinforcement Learning • 2B • Updated • 4 -
Jinyang23/Spark-1.5B-ScienceWorld
Reinforcement Learning • 2B • Updated • 11 -
Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
Paper • 2601.20209 • Published • 24
OPID
Spark
-
Jinyang23/Spark-1.5B-WebShop
Reinforcement Learning • 2B • Updated • 2 • 1 -
Jinyang23/Spark-1.5B-ALFWorld
Reinforcement Learning • 2B • Updated • 4 -
Jinyang23/Spark-1.5B-ScienceWorld
Reinforcement Learning • 2B • Updated • 11 -
Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
Paper • 2601.20209 • Published • 24
models 11
Jinyang23/Journal-WebShop-7B
Updated
Jinyang23/Journal-ScienceWorld-7B
Updated
Jinyang23/Journal-AlfWorld-7B
Updated
Jinyang23/EKGPO-WebShop-7B
Updated
Jinyang23/EKGPO-ScienceWorld-7B
Updated
Jinyang23/EKGPO-AlfWorld-7B
Updated
Jinyang23/OPID-ALFWorld-1.7B
Reinforcement Learning • 2B • Updated • 109 • 1
Jinyang23/Maestro-4B
5B • Updated • 2
Jinyang23/Spark-1.5B-ScienceWorld
Reinforcement Learning • 2B • Updated • 11
Jinyang23/Spark-1.5B-WebShop
Reinforcement Learning • 2B • Updated • 2 • 1