搜索结果

arxiv-latex MCP Server

MCP server that uses arxiv-to-prompt to fetch and process arXiv LaTeX sources for precise interpretation of mathematical expressions in scientific papers.

arXiv Search MCP Server

An MCP server that provides tools to search and fetch papers from arXiv.org.

Paper Search Mcp

MCP-server-HF-papers

This repository is an MCP server that let's me talk to HF daily papers via WhatsApp.

🎓 Semantic Scholar MCP Server

🔍 This project implements a Model Context Protocol (MCP) server for interacting with the Semantic Scholar API. It provides tools for searching papers, retrieving paper and author details, and fetching

Sci-Hub MCP Server

🔍 Enable AI assistants to search, access, and analyze academic papers through Sci-Hub using a simple MCP interface.

paperscraper-MCP-Server

A MCP Server for paperscraper：Tools to scrape publication metadata from pubmed, arxiv, medrxiv, biorxiv and chemrxiv.

Google Scholar MCP Server

A MCP Server for Google Scholar: 🔍 Enable AI assistants to search and access Google Scholar papers through a simple MCP interface.

arxiv-search MCP Server

A Model Context Protocol server for searching academic papers on arXiv.

PubMedSearch MCP Server

A Model Content Protocol server that provides tools to search and retrieve academic papers from PubMed database.

MCP Simple PubMed

MCP server for searching and querying PubMed medical papers/research database

Semantic Scholar API MCP server

MCP server for Semantic Scholar to search for papers

mcp-simple-arxiv

Tool to work with arXiv, provide LLM with ability to search and read papers from there

ArXiv MCP Server

A Model Context Protocol server for searching and analyzing arXiv papers

RWKV7-G1

RWKV开源发布了 RWKV7-G1 1.5B 推理模型（Reasoning Model）。模型基于 World v3.5 数据集训练，包含更多小说、网页、数学、代码和 reasoning 数据，总数据为 5.16T tokens。其具备其它同尺寸模型不具备的推理能力和任务能力，同时还支持现实世界 100+ 种语言。 在实际测试中，RWKV7-G1 1.5B 模型的推理逻辑性较强，能够完成有难度的

Vid2World

Vid2World是清华大学联合重庆大学推出的创新框架，支持将全序列、非因果的被动视频扩散模型（VDM）转换为自回归、交互式、动作条件化的世界模型。模型基于视频扩散因果化和因果动作引导两大核心技术，解决传统VDM在因果生成和动作条件化方面的不足。Vid2World在机器人操作和游戏模拟等复杂环境中表现出色，支持生成高保真、动态一致的视频序列，支持基于动作的交互式预测。Vid2World为提升世界模

AlphaGenome

AlphaGenome是谷歌DeepMind推出的全新AI模型，能更深入地理解基因组。模型能接收长达100万个碱基对的DNA序列输入，预测数千种表征其调控活性的分子特性，评估基因变异的影响。模型基于卷积层、Transformer架构，训练数据来自大型公共数据库。模型具有长序列上下文与高分辨率、全面多模态预测、高效变异评分和新颖剪接点建模等优势，在多项基准测试中表现顶尖，基于API向非商业研究领域开

4D-LRM

4D-LRM（Large Space-Time Reconstruction Model）是Adobe研究公司、密歇根大学等机构的研究人员共同推出的新型4D重建模型。模型能基于稀疏的输入视图和任意时间点，快速、高质量地重建出任意新视图和时间组合的动态场景。模型基于Transformer的架构，预测每个像素的4D高斯原语，实现空间和时间的统一表示，具有高效性和强大的泛化能力。4D-LRM在多种相机设