Alignment GitHub Repositories

Flexible and powerful data analysis / manipulation library for Python, providing labeled data structures similar to R data.frame objects, statistical functions, and much more

Automagically synchronize subtitles with video.

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network (ECCV 2018)

SmartSystemMenu extends system menu of all windows in the system

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

aeneas is a Python/C library and a set of tools to automagically synchronize audio and text (aka forced alignment)

DECA: Detailed Expression Capture and Animation (SIGGRAPH 2021)

Textbook on reinforcement learning from human feedback

Table Maker for Modern C++

MMseqs2: ultra fast and sensitive search and clustering suite

WFGY is heading toward WFGY 5.0 Polaris Protocol, a major open-source release for AI reasoning, RAG, agents, and real-world workflows. Includes Problem Map, Global Debug Card, WFGY 4.0, and the CFV Easter Egg.

"Automatic Language-Agnostic Subtitle Synchronization"

Secrets of RLHF in Large Language Models Part I: PPO

A collection view layout that gives you control over the horizontal and vertical alignment of the cells.

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.

DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.   🤖💤

Detect and fix struct field alignment to reduce memory usage in Go programs

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

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

A library with extensible implementations of DPO, KTO, PPO, ORPO, and other human-aware loss functions (HALOs).

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

一站式全自动字幕生成软件，下载、转录、翻译、压制全流程覆盖，无需人工介入 / One-stop automated subtitle generator. Handles downloading, transcription, translation, and hardcoding—zero human intervention required.

OpenJudge: A Unified Framework for Holistic Evaluation and Quality Rewards

A Go package for engineering organisms.

Prompt engineering for developers

🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.

Awesome papers involving LLMs in Social Science.

Precisely align, move, and measure+match objects and mesh parts in your 3D scenes.

An alignment plugin for Sublime Text using regular expression