post-training
Tracked open-source repos tagged post-training, sorted by stars.
Related topics
Topics that frequently appear alongside post-training on the same repo.
Recent risers
Repos created in the last 90 days, tagged post-training.
- #1
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
★ 1,334
- #1
A unified inference and post-training framework for accelerated video generation.
★ 4,300+150Star change over the last 7 days - #2
Awesome Reasoning LLM Tutorial/Survey/Guide
★ 2,533+6Star change over the last 7 days - #3
心理健康大模型 (LLM x Mental Health), Pre & Post-training & Dataset & Evaluation & Depoly & RAG, with InternLM / Qwen / Baichuan / DeepSeek / Mixtral / LLama / GLM series models
★ 1,781+1Star change over the last 7 days - #4
The living ecosystem where AI agents complete tasks through workflow loops, improve through iterative execution, are evaluated by mentor agents or humans in the loop, and turn completed work into reusable work experience and data to improve future agents.
★ 1,334+0Star change over the last 7 days - #5
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
★ 786+26Star change over the last 7 days - #6
Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)
★ 642+2Star change over the last 7 days - #7
Explore the Multimodal “Aha Moment” on 2B Model
★ 623+0Star change over the last 7 days - #8
[ACL 2026 Oral] "LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?"
★ 610+2Star change over the last 7 days - #9
An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale
★ 591+10Star change over the last 7 days - #10
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
★ 548+9Star change over the last 7 days - #11
[NeurIPS 2025 Spotlight] LLM post-training suite — featuring ReasonFlux, ReasonFlux-PRM, and ReasonFlux-Coder.
★ 542+0Star change over the last 7 days - #12★ 533+0Star change over the last 7 days
