PPL
Yifan Zhou
Papers (5)
SkillGenBench: Benchmarking Skill Generation Pipelines for LLM AgentsA World Model of Radiologist Reading for Medical Image Representation LearningInstruction Tuning Changes How Upstream State Conditions Late Readout: A Cross-Patching DiagnosticThe Convergence Gap: Instruction-Tuned Language Models Stabilize Later in the Forward PassStraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction