notes

research and engineering notes on medical AI, scientific computing, safe RL, generative modeling, contrastive learning, and large-model systems


Modern RL Objectives in Code: Bellman Targets, Trust Regions, PPO Clip, KL Estimators, and LLM Token/Sequence Granularity

从 Bellman target、policy gradient、TRPO trust region、PPO clip 与 KL estimator 出发，围绕 reward shaping、advantage 粒度、importance ratio/clip 单位和 loss aggregation，拆解 PPO、GRPO、DAPO、Dr. GRPO、CISPO、GSPO、DPO 及 training-inference mismatch。

51 min read   ·   2026

Orthogonal Polynomials for Uncertainty Quantification: Recurrence Algorithms, PCE, and Biomedical Simulation

A research-level map of orthogonal polynomial recurrence algorithms, polynomial chaos expansion, and noninvasive uncertainty quantification for biomedical simulations.

9 min read   ·   2025

Contrastive Learning: Objectives, Dictionaries, Momentum Encoders, and Multimodal Alignment

从 anchor/positive/negative、dictionary 与 temperature 出发，梳理 Triplet、NCE/InfoNCE、NT-Xent、MoCo/SimCLR、BYOL/SimSiam/DINO、CLIP 以及 ArcFace/CosFace 的候选集合与表征几何。

36 min read   ·   2025

a distill-style blog post

an example of a distill-style blog post and main elements

25 min read   ·   2021

a post with code

an example of a blog post with some code

4 min read   ·   2015