post-training

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

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.

Official Codebase for "Neural Thickets: Diverse Task Experts Are Dense Around Pretrained Weights" (ICML 2026 Spotlight)

Explore the Multimodal “Aha Moment” on 2B Model

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.

LLMInternSkill: LLM internship resume and job-search Codex Skill for resume polish, JD tailoring, evidence guard, interview grilling, and Project Scout. 大模型实习简历与求职工具箱。

Train a Language Model with GRPO to create a schedule from a list of events and priorities

A collection of vision-language-action model post-training methods.

RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning

Developer Hub for NVIDIA Alpamayo, containing ready-to-use recipes for fine-tuning, reinforcement-learning post-training, quantization, and deployment.

[ECCV 2026🔥] SRUM: Fine-Grained Self-Rewarding for Unified Multimodal Models

A High-Efficiency System of Large Language Model Based Search Agents

Code repository dedicated to experimenting and research with tiny reasoning language model

This repository collects awesome representative papers and resources for "From Pre-training to Post-training: A Survey on Time Series Foundation Models" (TechRxiv-26).

Lightweight replication study of DeepSeek-R1-Zero. Interesting findings include "No Aha Moment", "Longer CoT ≠ Accuracy", and "Language Mixing in Instruct Models".

[EMNLP 2022] Continual Training of Language Models for Few-Shot Learning

Pure RL to post-train base models for social reasoning capabilities. Lightweight replication of DeepSeek-R1-Zero with Social IQa dataset.

[AAAI 2026] D²PPO: Diffusion Policy Policy Optimization with Dispersive Loss.

Code repository for "Post-pre-training for Modality Alignment in Vision-Language Foundation Models" (CVPR2025)