MiroMind-M1: Redefining Open-Source Mathematical Reasoning for AI Open-source AI is entering a new phase, with MiroMind-M1 leading the charge in mathematical reasoning. This project goes beyond simply releasing models by offering full transparency, every model, data... AI transparency CAMPO chain-of-thought large language models mathematical reasoning open-source AI reinforcement learning token efficiency
Open Deep Search: Unlocking Advanced AI Search for Everyone Imagine if the power behind today’s smartest search engines was no longer limited to tech giants. That’s the promise of Open Deep Search (ODS), a breakthrough open-source framework that puts advanced ... AI search benchmarks community innovation information retrieval large language models machine learning open-source reasoning agents
NVIDIA Helix Parallelism Powers Real-Time AI with Multi-Million Token Contexts AI assistants recalling months of conversation, legal bots parsing vast case law libraries, or coding copilots referencing millions of lines of code, all while delivering seamless, real-time responses... AI inference GPU optimization KV cache large language models NVIDIA Blackwell parallelism real-time AI
MIT’s CodeSteer Is Coaching AI to Outsmart Complex Problems MIT researchers have built CodeSteer, a smart assistant designed to help large language models (LLMs) seamlessly alternate between generating text and writing code by utilizing a "coach" to evaluate t... AI code generation CodeSteer large language models machine learning MIT research problem solving symbolic reasoning
AI in Radiology: RadGPT is Making Medical Reports Patient-Friendly Medical reports, especially those in radiology, are often filled with terminology that can overwhelm even the most diligent patient. Now, Stanford researchers are changing the landscape with RadGPT , ... AI healthcare large language models medical reports patient communication RadGPT radiology Stanford research
Feedback-Driven Methods Are Transforming Prompt Engineering Prompt engineering is crucial for maximizing the capabilities of large language models (LLMs), but it has traditionally required significant manual effort and specialized know-how. As new tasks and mo... AI research automation efficiency feedback loops large language models machine learning prompt optimization
Large Reasoning Models: Breakthroughs and Breaking Points in AI Problem-Solving Artificial intelligence has made remarkable strides, and Large Reasoning Models (LRMs) are at the forefront of this revolution. These models promise to deliver more than just answers, they aim to repl... AI research artificial intelligence benchmarking chain-of-thought large language models model limitations problem complexity reasoning
vLLM Is Transforming High-Performance LLM Deployment Deploying large language models at scale is no small feat, but vLLM is rapidly emerging as a solution for organizations seeking robust, efficient inference engines. Originally developed at UC Berkeley... AI inference GPU optimization Kubernetes large language models memory management model deployment vLLM
How CACTUS Bridges AI and Cheminformatics for Accelerated Molecular Discovery Recent breakthroughs in artificial intelligence promise to revolutionize drug discovery, yet most language models struggle with the complexity of chemistry. CACTUS, a new open-source agent, aims to ch... AI agents cheminformatics drug discovery large language models molecular analysis open source prompt engineering
How AI Is Changing Pediatric ADHD Chart Reviews and Care Imagine transforming weeks of tedious chart reviews into just minutes of actionable insights. This is now possible thanks to Stanford Medicine researchers, who leveraged artificial intelligence ( AI )... ADHD AI clinical care ethics healthcare research large language models medical records pediatrics
Themis AI Is Teaching AI Models to Recognize Their Own Uncertainty Artificial intelligence is making waves in critical industries, yet a major challenge remains: most AI systems struggle to recognize and communicate when they are unsure. The risks become clear in hig... AI uncertainty bias detection drug discovery edge computing large language models machine learning model reliability
Automated Model Merging: How Evolutionary Optimization is Democratizing AI Innovation Building advanced AI models has traditionally required vast computational resources, high costs, and significant environmental impact. Now, a new method—evolutionary optimization for automated model m... AI models cross-domain AI evolutionary algorithms large language models machine learning optimization model merging open source AI