Avatar 🍥

Mao Song(毛松)'s Homepage

Never stop learning.

  1. Bilibili
  2. Google Scholar
  1. Home
  2. Archives
  3. Search
  4. About
  5. Tags
    1. Dark Mode

Archives

2025 69
2024 51
2023 1

Categories

LLM LeetCode MLLM Reasoning Infra Machine Learning NLP Terminal Deep Learning RAG 随笔

Tags

Medium Qwen Reasoning DFS Attention Matrix Array DP String Tree BFS Bit Manipulation Hard Distributed Training Easy Kimi Optimizer RL Transformer GRPO
LLM

Unified perspective on dLLM and LLM

MLE和KL divergence之间的等价性推导

Jun 28, 2025
1 minute read
Machine Learning

Relationship between MLE and KL divergence

MLE和KL divergence之间的等价性推导

Jun 27, 2025
2 minute read
MLLM Reasoning

Notes on MiMo-VL

MiMo-VL基于MiMo-7B,是一个多模态推理大语言模型

Jun 05, 2025
3 minute read
LLM

Hands on LLM(1) Tokenizer

Tokenizer总结与BPE的高效实现

May 24, 2025
12 minute read
LLM

Notes on attention bias

为什么transformer没有QKV bias

May 22, 2025
6 minute read
1 … 8 9 10 … 25
© 2020 - 2025 Mao Song(毛松)'s Homepage
Built with Hugo
Theme Stack designed by Jimmy