Stars
PointNet and PointNet++ implemented by pytorch (pure python) and on ModelNet, ShapeNet and S3DIS.
This project is divided in two parts: the Python part, classifies point clouds with PointNet architecture and the C++ part, extracts and measures the volume of the point clouds with PCL and OpenCV
PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space
Janus-Series: Unified Multimodal Understanding and Generation Models
LLM-powered multiagent persona simulation for imagination enhancement and business insights.
This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and developing research plans.
GRUtopia: Dream General Robots in a City at Scale
Tool Learning for Big Models, Open-Source Solutions of ChatGPT-Plugins
[NeurIPS'23 Spotlight] Segment Any Point Cloud Sequences by Distilling Vision Foundation Models
🤖 AgentVerse 🪐 is designed to facilitate the deployment of multiple LLM-based agents in various applications, which primarily provides two frameworks: task-solving and simulation
A programming framework for agentic AI 🤖 PyPi: autogen-agentchat Discord: https://aka.ms/autogen-discord Office Hour: https://aka.ms/autogen-officehour
An Autonomous LLM Agent for Complex Task Solving
[ACL 2024] Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
Must-read Papers on Knowledge Editing for Large Language Models.
An Open-sourced Knowledgable Large Language Model Framework.
BELLE: Be Everyone's Large Language model Engine（开源中文对话大模型）
Finetune Qwen3, Llama 4, TTS, DeepSeek-R1 & Gemma 3 LLMs 2x faster with 70% less memory! 🦥
An efficient, flexible and full-featured toolkit for fine-tuning LLM (InternLM2, Llama3, Phi3, Qwen, Mistral, ...)
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
The official implementation of RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/
the AI-native open-source embedding database
哔哩下载姬downkyi，哔哩哔哩网站视频下载工具，支持批量下载，支持8K、HDR、杜比视界，提供工具箱（音视频提取、去水印等）。
Bottoms Up Development with LlamaIndex - Building a Documentation Chatbot
Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)
Question and Answer based on Anything.
[EMNLP'23, ACL'24] To speed up LLMs' inference and enhance LLM's perceive of key information, compress the prompt and KV-Cache, which achieves up to 20x compression with minimal performance loss.