AI Agent Achieves Gold Medal Performance on IPhO 2025 Physics Competition In a remarkable demonstration of artificial intelligence's advancing capabilities, researchers from Princeton University and collaborating institutions have developed Physics Supernova, an AI agent sy...
Microsoft VibeVoice: Long-Form Conversational Speech Synthesis Few technologies capture the imagination quite like text-to-speech synthesis. While we've seen remarkable progress in generating natural-sounding speech for short sequences, a significant frontier has... artificial intelligence conversational AI machine learning microsoft research open source speech synthesis text-to-speech
Surya: The Open-Source AI Solar Forecasting Model Thanks to Surya, a pioneering AI model co-developed by IBM and NASA, we could potentially anticipate powerful solar storms hours before they threaten our technology or astronauts in space. Surya stand... AI foundation model heliophysics IBM NASA open source solar research space weather
SemTools: Command-Line Mastery for Document Parsing and Semantic Search In an era where documents are becoming increasingly complex and information overload is the norm, developers need tools that can slice through the noise with surgical precision. This is where SemTools... ai agents cli document parsing llamaindex open source rust semantic search
mmBERT: How Johns Hopkins Built a 1,833-Language AI That Outperforms XLM-R mmBERT: How Johns Hopkins Built a 1,833-Language AI That Outperforms XLM-R Imagine trying to build an AI system that truly understands human language not just in English, but in over 7,000 languages s... AI research annealed language learning cross-lingual digital inclusion encoder-only FlashAttention Gemma tokenizer GLUE inverse masking language model mmBERT ModernBERT MTEB multilingual NLP XLM-R XTREME
Agentic Web Interfaces: Building Websites That Welcome AI Agents The paper "Build the web for agents, not agents for the web" proposes a reorientation of how we design the modern web: rather than forcing AI systems to operate through human-centered pages, we should... AWI MCP Playwright Safety web agents WebArena
AI Meets Penetration Testing: Exploring BruteForceAI's Game-Changing Automation Security professionals are reimagining their approach to web application assessments thanks to the rise of artificial intelligence. Tools like BruteForceAI now make it possible to discover and test lo... artificial intelligence brute-force attacks cybersecurity tools ethical hacking login page detection penetration testing web application security
LangExtract: Grounded, Structured Extraction for Long Text LangExtract is a focused open-source library from Google that turns unstructured text into structured data you can trust. It combines schema-guided prompts, precise span alignment to the source text, ... Gemini information extraction langextract LLM NLP Ollama OpenAI plugins Python
UI-TARS-2: Scaling GUI-Centered Agents With Multi-Turn RL Modern AI agents are learning to use computers like humans do. They can navigate websites, manage files, and even play games by controlling desktop and mobile interfaces directly. This paper introduce... AI agents Benchmarking Data Flywheel GUI Parameter Interpolation Reinforcement Learning
The Model Context Protocol Registry: Building the Backbone for AI Server Discovery The Model Context Protocol Registry is an open, standards-driven catalog and API for MCP servers. If you are building or running AI tools that speak MCP, the registry is the connective tissue that tur... AI registry API DevOps Enterprise Go Kubernetes MCP Open source Package validation Subregistries
Firecrawl: The Web Data API That's Upending How We Scrape the Internet firecrawl Organization firecrawl The Web Data API for AI - Turn entire websites into LLM-ready markdown or structured data 🔥 55.9k 4.7k 201 GNU Affero General Public License v3.0 Homepage 66.6k KB 4.7... ai api javascript open-source python typescript web-scraping
MCP Registry Preview Transforms Server Discovery and Collaboration The launch of the Model Context Protocol (MCP) Registry signals a new era for discoverability and collaboration within the ecosystem. This open, centralized catalog and public API are designed to make... AI applications API community MCP open source server registry sub-registries