Stars
World Simulator Assistant for Physics-Aware Text-to-Video Generation
AppPlatform 是一个前沿的大模型应用工程，旨在通过集成的声明式编程和低代码配置工具，简化和优化大模型的训练与推理应用的开发过程。本工程为软件工程师和产品经理提供一个强大的、可扩展的环境，以支持从概念到部署的全流程 AI 应用开发。
Matrix-Game: Interactive World Foundation Model
From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery
[RA-L 2025 Accept without Revision] A stereo visual-inertial odometry system based on voxel map
Turn detection for full-duplex dialogue communication
[T-PAMI 2025] Official implementation for "SVGDreamer++: Advancing Editability and Diversity in Text-Guided SVG Generation" https://arxiv.org/abs/2411.17832
Vexa is a decentralized AI agent platform built on BNB Chain.
Improvements to animations based on Manim, designed to facilitate the demonstration of algorithms in data structures, operating systems, and computer organization principles.
BIRD-CRITIC 1.0: Can Large Language Models Solve USER SQL Issues in Real-World Database Applications?
Code for our paper "Towards Trustworthy Dataset Distillation" (Pattern Recognition 2025)
AI-Powered Python & Python-Powered AI (Python-Use)
Klavis AI (YC X25): Open Source MCP integration for AI applications
DeepRetrieval - 🔥 Training Search Agent with Retrieval Outcomes via Reinforcement Learning
Dataset approched by A Benchmark and Frequency Compression Method for Infrared Few-Shot Object Detection
ACI.dev is the open source platform that connects your AI agents to 600+ tool integrations with multi-tenant auth, granular permissions, and access through direct function calling or a unified MCP …
✨✨latest advancements in VLA models(VIsion Language Action)
A curated list of awesome papers on the platonic representation hypothesis.
[CVPR 2025] Official implementation for "Empowering LLMs to Understand and Generate Complex Vector Graphics" https://arxiv.org/abs/2412.11102
mcp client for Go (Golang). Integrate multiple Model Context Protocol (MCP) servers
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds
[CVPR 2025 Highlight] Official code for "Olympus: A Universal Task Router for Computer Vision Tasks"
A comprehensive React-based stock market analysis dashboard that enables users to visualize and compare historical market data from multiple stocks, featuring technical indicators, trend analysis, …
A post-training method to enhance CLIP's fine-grained visual representations with generative models.