post-training

PipelineLLM 是一个系统性的大语言模型（LLM）后训练学习项目，涵盖从监督微调（SFT）到偏好优化（DPO）、强化学习（RLHF/PPO/GRPO）再到持续学习（Continual Learning)的完整技术栈。

A lightweight post-training framework for LLMs and VLMs. 51 algorithms, 38 verified models. Scales with DeepSpeed, vLLM, and Ray.

[ICML 2025] Vulnerability-Aware Alignment: Mitigating Uneven Forgetting in Harmful Fine-Tuning

[🔥 ICLR 2026] - Misaligned Roles, Misplaced Images: Structural Input Perturbations Expose Multimodal Alignment Blind Spots

Sudoku4LLM is a Sudoku dataset generator for training and evaluating reasoning in Large Language Models (LLMs). It offers customizable puzzles, difficulty levels, and 11 serialization formats to support structured data reasoning and Chain of Thought (CoT) experiments.