Tingyu Zhang

Thoughts on reinforcement learning, math, and engineering

KL-Divergence and Entropy

The origin of care divergence and why it has such property.

1 min read · November 01, 2026

2026 · Machine Learning Reinforcement Learning Artificial Intelligence · Machine Learning
The Bradley-Terry Model

From pairwise comparisons to RLHF reward models

7 min read · August 21, 2026

2026 · Machine Learning Reinforcement Learning Artificial Intelligence · Machine Learning
Dynamic Programming and Differential Equation

My blog about DP.

7 min read · March 30, 2026

2026 · Algorithm Mathematics · Programming
How to understand RoPE

Today I fully understand every part of RoPE, so I wanna generate a note to record.

3 min read · March 20, 2026

2026 · AI Algorithm Mathematics · AI
Nim Problem

A thought for Leecode problem

2 min read · March 17, 2026

2026 · Programming Game Theory · Programming