🔄 In a Training Loop

Honglin Lin

LHL3341

·

https://lhl3341.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 14 days ago

HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offs

authored a paper 14 days ago

ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL

authored a paper 14 days ago

Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs

View all activity

Organizations

LHL3341 's Spaces 1

Croissant Checker - Dev