PPL
Hongyu Lin
Papers (5)
LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language AgentsA Case for Agentic Tuning: From Documentation to Action in PostgreSQLVision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-DistillationCompositional Sparsity as an Inductive Bias for Neural Architecture DesignLearning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards