HuskyInSalt

FoR. [ICML 2025] Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples

GenerativeAgentsCN. 本项目为Generative Agents项目的重构+深度汉化版本，旨在为中文用户提供一个利于维护的基础版本，以便后续实验或功能拓展。

awesome-ai-research-writing. Elevate your AI research writing, no more tedious polishing ✨

ESP32-S3-Touch-AMOLED-2.16. ESP32-S3-Touch-AMOLED-2.16 Engineering Sample Program

AI-Desktop-Pet. 一个简单的AI桌宠，能够实现陪聊（语音输入和文字输入），长期记忆，以及视觉、发声(tts)功能

web-content-fetcher. Python

colleague-skill. 将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶

trl. Train transformer language models with reinforcement learning.

Awesome-Forgetting-in-Deep-Learning. A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning. TPAMI, 2024.

DRAGIN. Source code of DRAGIN, ACL 2024 main conference Long Paper (Oral)

SeaKR. Python

llama_index. LlamaIndex is the leading document agent and OCR platform

Entriever. Code for "Entriever: Energy-based Retriever for Knowledge-Grounded Dialog Systems" (ACL2025 findings)

AdaRAGUE. [ACL 2025] Adaptive Retrieval without Self-Knowledge? Bringing Uncertainty Back Home

RLPR. Extrapolating RLVR to General Domains without Verifiers

Logic-RL. Reproduce R1 Zero on Logic Puzzle

verl. verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

hotpot. Python

ret-robust. Implementation of the paper: "Making Retrieval-Augmented Language Models Robust to Irrelevant Context"

InstructRAG. [ICLR 2025] InstructRAG: Instructing Retrieval-Augmented Generation via Self-Synthesized Rationales

xRAG. [Neurips2024] Source code for xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token

direct-preference-optimization. Reference implementation for DPO (Direct Preference Optimization)

LLMDataHub. A quick guide (especially) for trending instruction finetuning datasets

large-qa-datasets. A collection of large question answering datasets

awesome-llm-attributions. A Survey of Attributions for Large Language Models

RAG-Survey. Collecting awesome papers of RAG for AIGC. We propose a taxonomy of RAG foundations, enhancements, and applications in paper "Retrieval-Augmented Generation for AI-Generated Content: A Survey".

self-rag. This includes the original implementation of SELF-RAG: Learning to Retrieve, Generate and Critique through self-reflection by Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi.

GPT-SoVITS. 1 min voice data can also be used to train a good TTS model! (few shot voice cloning)