A pytorch implementation of the paper "TreeLoRA: Efficient Continual Learning via Layer-Wise LoRAs Guided by a Hierarchical Gradient-Similarity Tree".

https://dev.to/answeryt/the-demo-spell-and-production-dilemma-of-ai-agents-how-i-built-a-self-learning-agent-system-4okk

Syllable Analysis Data Augmentation (SADA), This project introduces a glyph dictionary and grammar-aware augmentation strategy designed to enhance Khmer palm leaf manuscript recognition. By modelin…

NeuralOM: Neural Ocean Model for Subseasonal-to-Seasonal Simulation

Tego is a pluggable Node.js framework for building customizable development platforms. It enables developers to create their own no-code/low-code systems or event-driven applications, while the cor…

Hierarchical Reasoning Model Official Release

A repo to develop an AI agent project

新数据洞察方式

GENERanno: A Genomic Foundation Model for Metagenomic Annotation

Elasticsearch GUI client for Mac, windows and linux, Opensearch GUI client for Mac, windows and linux

We introduce the Audio Logical Reasoning (ALR) dataset, consisting of 6,446 text-audio annotated samples specifically designed for complex reasoning tasks. Building on this resource, we propose Sou…

s3 - Efficient Yet Effective Search Agent Training via RL for RAG

An efficient storage and compute engine for both on-prem and cloud-native data analytics.

AI Manus is a general-purpose AI Agent system that supports running various tools and operations in a sandbox environment.

An intelligent development and testing platform designed to empower small and medium-sized enterprises to build their own R&D systems, streamline workflows, and enhance operational efficiency.

🌐Web Agent Protocol (WAP) - Record and replay user interactions in the browser with MCP support

OpenAPIDesigner is an open-source OpenAPI specification design tool that allows developers to design, write, and validate OpenAPI specifications.

[RA-L 2025 Accept without Revision] A stereo visual-inertial odometry system based on voxel map

Train your Agent model via our easy and efficient framework

Matrix-Game: Interactive World Foundation Model

Skywork-R1V2:Multimodal Hybrid Reinforcement Learning for Reasoning (Best open-source multimodal reasoning model)

[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer

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。

Klavis AI (YC X25): Open Source, easy to use MCPs on Slack, Discord and Web

🔥 InfiniteYou: Flexible Photo Recrafting While Preserving Your Identity

TVM Documentation in Chinese Simplified / TVM 中文文档

AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai