Self-evolving Context Database for AI Agents. Unify Agent Memory, Knowledge RAG and Skills.

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

Bella is best

本项目为xiaozhi-esp32提供后端服务，帮助您快速搭建ESP32设备控制服务器。Backend service for xiaozhi-esp32, helps you quickly build an ESP32 device control server.

Paper list for Efficient Reasoning.

ACE-Step: A Step Towards Music Generation Foundation Model

The simplest, fastest repository for training/finetuning small-sized VLMs.

Academic Survey Paper Generation.

The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

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

No fortress, purely open ground. OpenManus is Coming.

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

[EMNLP 2024 Main] Official implementation of the paper "Unveiling In-Context Learning: A Coordinate System to Understand Its Working Mechanism".

Towards Generalized and Efficient Blackbox Optimization System/Package (KDD 2021 & JMLR 2024)

✨✨A curated list of latest advances on Large Foundation Models with Federated Learning

LLM training in simple, raw C/CUDA

🙌 OpenHands: AI-Driven Development

[AAAI 2025] Official implementation of "OOTDiffusion: Outfitting Fusion based Latent Diffusion for Controllable Virtual Try-on"

The official PyTorch implementation of Google's Gemma models

Awesome LLM compression research papers and tools.

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Question and Answer based on Anything.

A scikit-learn-compatible library for estimating prediction intervals and controlling risks, based on conformal predictions.

Robust recipes to align language models with human and AI preferences

[IJCAI 2024] FactCHD: Benchmarking Fact-Conflicting Hallucination Detection

https://acl2023-retrieval-lm.github.io/