# mli/paper-reading

深度学习经典、新论文逐段精读

Repository: https://github.com/mli/paper-reading
Canonical: https://ross.abutalabs.com/products/paper-reading
License: Apache-2.0
License Family: permissive
Topics: deep-learning, paper, reading-list
Last push: 2025-03-22T03:49:35+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 12, release rhythm 35, longevity 100
- inputs: {"age_days": 1776, "days_push": 529, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 33735, forks 2806 (observed 2026-08-28T04:11:58.410043+00:00)

## What it is
A curated collection of in-depth video walkthroughs of classic and recent deep learning papers, presented paragraph by paragraph by Mu Li. The repository indexes recorded lectures (on Bilibili and YouTube) covering papers like Sora, Llama 3.1, and GPT-4.

## Use cases
- learn deep learning by reading classic papers
- understand the Llama 3.1 paper in detail
- find guided explanations of GPT-4 and Sora papers
- get a reading list of important ML papers
- watch paper walkthroughs with expert commentary

## When to choose
- you want expert, paragraph-by-paragraph explanations of landmark deep learning papers
- you prefer video lectures over reading papers alone
- you want a curated, continuously updated paper reading list

## When to avoid
- you need runnable code or a software tool rather than educational content
- you need English-only content since lectures are in Chinese
- you want interactive tutorials or exercises

## Facets
- artifact type: learning-resource
- maturity: active
- function: deep-learning, documentation
- domain: deep-learning, large-language-models, tutorials
- platform: -
- tags: paper-reading, video-lectures, reading-list, bilibili, chinese-content, web-server

## Member repositories
- mli/paper-reading (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:11:58.410043+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T16:28:09.178865+00:00, confidence not recorded.
  - readme: https://github.com/mli/paper-reading (fetched 2026-08-28T04:11:58.410043+00:00, sha 00b6e454a3d4)
- Data as of 2026-08-30T08:39:29.467469+00:00.