Rank #8,416 611 starsPython

LightReasoner

by HKUDS (organization)

[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?" (description from the project’s GitHub page)

View on GitHub Homepage

Repository facts

Stars: 611
Forks: 34
Open issues and pull requests: 2
Primary language: Python
License: MIT License (MIT)
Owner: HKUDS · Organization
Created: Sep 29, 2025
Last push: May 22, 2026

Topics

Rank #8,416 of 9,507 in AI on GitHub, by stars. Data from the GitHub API, fetched Oct 18, 2026; star counts change daily. Stars measure popularity, not quality or safety, and a listing is not an endorsement. How this list is made

Add this badge to your README

Ranked #8,416 in AI on GitHub Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges

Markdown (for a README)

[![Ranked #8,416 in AI on GitHub](https://unitedstatesofamericasuperintelligence.com/badges/github/hkuds--lightreasoner.svg)](https://unitedstatesofamericasuperintelligence.com/github/hkuds--lightreasoner/)

HTML

<a href="https://unitedstatesofamericasuperintelligence.com/github/hkuds--lightreasoner/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/hkuds--lightreasoner.svg" alt="Ranked #8,416 in AI on GitHub" height="20"></a>

Projects that share this one’s GitHub topics.

Rank 2,469: MiniMax-AI/MiniMax-M1
MiniMax-M1, the world's first open-weight, large-scale hybrid-attention reasoning model.
3,185 starsPythonApache-2.0Last push Jul 7, 2025
Rank 1,483: rasbt/reasoning-from-scratch
Implement a reasoning LLM in PyTorch from scratch, step by step
5,425 starsJupyter NotebookApache-2.0Last push Oct 2, 2026
Rank 4,095: TokenRhythm/NeoHorse
NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness.
1,736 starsPythonApache-2.0Last push Sep 26, 2026
Rank 6,932: whitecircle/halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
825 starsPythonOther licenseLast push Oct 15, 2026
Rank 8,081: sunrainyg/RandOpt
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
653 starsPythonNo license file detectedLast push Sep 21, 2026
Rank 978: zilliztech/deep-searcher
Open Source Deep Research Alternative to Reason and Search on Private Data. Written in Python.
8,342 starsPythonApache-2.0Last push Sep 22, 2026

Repository facts

Topics

Add this badge to your README

Related projects

Rank 2,469: MiniMax-AI/MiniMax-M1

Rank 1,483: rasbt/reasoning-from-scratch

Rank 4,095: TokenRhythm/NeoHorse

Rank 6,932: whitecircle/halo

Rank 8,081: sunrainyg/RandOpt

Rank 978: zilliztech/deep-searcher

Support Us