Reading notes
Topics
Living, topic-level collections of papers, concise summaries, and research questions.
Agent Environments
Executable environments, scalable synthesis, verification, benchmarks, and training signals for interactive agents.
Open collection →LLM Reinforcement Learning
From PPO to GRPO, with emphasis on the staleness–stability–efficiency trade-off.
Open collection →MRI Notes Archive
Earlier reading and working notes on ASL, reconstruction, sampling, diffusion MRI, and imaging foundations.
Open archive →