Popular GitHub Repositories for Alignment

Secrets of RLHF in Large Language Models Part I: PPO

Official PyTorch Implementation of "GAN-Supervised Dense Visual Alignment" (CVPR 2022 Oral, Best Paper Finalist)

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & Vertical Distillation of LLMs.

FaceXlib aims at providing ready-to-use face-related functions based on current STOA open-source methods.

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

Prompt engineering for developers

[ICLR 2025] Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing. Your efficient and high-quality synthetic data generation pipeline!

A framework to evaluate the generalization capability of safety alignment for LLMs

Deita: Data-Efficient Instruction Tuning for Alignment [ICLR2024]

Textbook on reinforcement learning from human feedback

Awesome papers involving LLMs in Social Science.

An opensource ChatBot built with ExpertPrompting which achieves 96% of ChatGPT's capability.

AlignProp uses direct reward backpropogation for the alignment of large-scale text-to-image diffusion models. Our method is 25x more sample and compute efficient than reinforcement learning methods (PPO) for finetuning Stable Diffusion

face detection alignment recognition reconstruction ...

InsTag: A Tool for Data Analysis in LLM Supervised Fine-tuning

Facial Landmark Detection based on PyTorch

Aligner for text-to-speech

Python package for extracting representations from state-of-the-art computer vision models

A continually updated list of literature on Reinforcement Learning from AI Feedback (RLAIF)

The collection of awesome papers on alignment of diffusion models.