AI Frontiers
Nouvelles et reportages
Orca-AgentInstruct: Agentic flows can be effective synthetic-data generators
| Arindam Mitra, Ahmed Awadallah, et Yash Lara
Orca-AgentInstruct, from Microsoft Research, can generate diverse, high-quality synthetic data at scale to post-train and fine-tune base LLMs for expanded capabilities, continual learning, and increased performance.
Research Focus: Week of October 28, 2024
New Research | FLASH: Workflow automation agent for diagnosing recurring incidents; METAREFLECTION: Learning instructions for language agents using past reflections; Boosting LLM training efficiency through faster communication between GPUs; and more.
Dans l’actualité | Eye on AI (podcast)
Why AI Agents Are the Next Big Thing in Tech
In this episode of the Eye on AI podcast, we dive deep into the world of AI agents with Ece Kamar, VP of Research and Managing Director of AI Frontiers Lab at Microsoft. Ece shares her unique insights on the…
Microsoft Research Forum Episode 4: The future of multimodal models, a new “small” language model, and other AI updates
Explore multimodal & small language models, plus advanced benchmarks for AI evaluation. Microsoft researchers are working on breakthroughs in weather prediction, materials design, even a new kind of computer for AI inference and hard optimization problems.
Eureka: Evaluating and understanding progress in AI
| Vidhisha Balachandran, Jingya Chen, Neel Joshi, Besmira Nushi, Hamid Palangi, Eduardo Salinas, Vibhav Vineet, James Woffinden-Luey, et Safoora Yousefi
How can we rigorously evaluate and understand state-of-the-art progress in AI? Eureka is an open-source framework for standardizing evaluations of large foundation models, beyond single-score reporting and rankings. Learn more about the extended findings.
In this episode, learn about the latest multimodal AI models, advanced benchmarks for AI evaluation and model self-improvement, and an entirely new kind of computer for AI inference and hard optimization. Discover how these research breakthroughs and more can help…
Tracing the path to self-adapting AI agents
| Ching-An Cheng, Adith Swaminathan, et Allen Nie
Introducing Trace, Microsoft and Stanford University’s novel AI optimization framework, now available as a Python library. Trace adapts dynamically and optimizes a wide range of applications from language models to robot control.
Abstracts: July 18, 2024
| Gretchen Huizinga et Arindam Mitra
Senior Researcher Arindam Mitra introduces AgentInstruct. Using raw data sources, the automated multi-agent framework can create diverse, high-quality synthetic data at scale for the post-training of small and large language models.
Dans l’actualité | Microsoft News Center
Why AI sometimes gets it wrong — and big strides to address it
Around the time GPT-4 was making headlines for acing standardized tests, Microsoft researchers and collaborators were putting other AI models through a different type of test — one designed to make the models fabricate information.