Jinyang Wu
Jinyang23
AI & ML interests
large language models, reasoning, agentic rl
Recent Activity
authored a paper about 12 hours ago
Two-Stage Regularization-Based Structured Pruning for LLMs authored a paper about 12 hours ago
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning upvoted a paper about 17 hours ago
PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement LearningOrganizations
None yet
Spark
-
Jinyang23/Spark-1.5B-WebShop
Reinforcement Learning • 2B • Updated • 10 • 1 -
Jinyang23/Spark-1.5B-ALFWorld
Reinforcement Learning • 2B • Updated • 10 -
Jinyang23/Spark-1.5B-ScienceWorld
Reinforcement Learning • 2B • Updated • 13 -
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 • 10 • 1 -
Jinyang23/Spark-1.5B-ALFWorld
Reinforcement Learning • 2B • Updated • 10 -
Jinyang23/Spark-1.5B-ScienceWorld
Reinforcement Learning • 2B • Updated • 13 -
Spark: Strategic Policy-Aware Exploration via Dynamic Branching for Long-Horizon Agentic Learning
Paper • 2601.20209 • Published • 24