notes

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


Modern Reinforcement Learning Objectives: Bellman Targets, PPO/TRPO, GRPO, DAPO, CISPO, and GSPO

A technical map of Bellman targets, policy gradients, trust-region optimization, PPO clipping, RLHF, DPO, and token- versus sequence-level objectives in modern LLM reinforcement learning.

44 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: From Sampling Strategies to Multimodal Representation Learning

从 Triplet、InfoNCE、NT-Xent 到 MoCo、SimCLR、DINO、CLIP 的统一视角。

29 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