Nouvelles et reportages

Research Focus: Week of October 23, 2023
In this issue: Kosmos-2.5: A Multimodal Literate Model; Can vine copulas explain complex relationships of weather variables; New system accelerates the adaptive training process; Structural inequalities and relational labor in the influencer industry.

What’s Your Story: Ranveer Chandra
| Johannes Gehrke et Ranveer Chandra
You may know tech, but how well do you know the people behind the advances? Ranveer Chandra talks about growing up in India, his work in systems and networking, and finding joy in your job in the first episode of…

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models
| Boxin Wang, Bo Li, et Zinan Lin
This paper received the outstanding benchmarks track paper award during NeurIPS 2023 (opens in new tab). How trustworthy are generative pre-trained transformer (GPT) models? To answer this question, University of Illinois Urbana-Champaign, together with Stanford University, University of California, Berkeley,…

Research Focus: Week of October 9, 2023
Research Focus: Principal researcher Lester Mackey recognized for pioneering statistical and ML techniques; Pareto frontiers in neural feature learning; structural inequality in the influencer industry; new research on cardinality estimation.

HoloAssist: A multimodal dataset for next-gen AI copilots for the physical world
| Xin Wang et Neel Joshi
HoloAssist is a new multimodal dataset consisting of 166 hours of interactive task executions with 222 participants. Discover how it offers invaluable data to advance the capabilities of next-gen AI copilots for real-world tasks.

Intern Insights: Dr. Madeleine Daepp with Jennifer Scurrell and Alejandro Cuevas
| Madeleine Daepp, Alejandro Cuevas, et Jennifer Scurrell
Connecting with researchers, collaborating across disciplines, and exploring a new city—PhD students Jennifer Scurrell and Alejandro Cuevas talk to Senior Researcher Madeleine Daepp about the internship experience at Microsoft Research.
Dans l’actualité | Medium: Jesus Rodriguez
Inside AutoGen: Microsoft Research New Autonomous Agent Framework
Autonomous agents are rapidly becoming one of the hottest trends in generative AI. Still far from being a solve problem or a mainstream trend, autonomous agents is universally acknowledged as one of the new frontiers in the foundation model landscape.…
Dans l’actualité | VentureBeat
Microsoft’s AutoGen framework allows multiple AI agents to talk to each other and complete your tasks
Microsoft has joined the race for large language model (LLM) application frameworks with its open source Python library, AutoGen. As described by Microsoft, AutoGen is “a framework for simplifying the orchestration, optimization, and automation of LLM workflows.” The fundamental concept…
Dans l’actualité | isp.page
The Revolution of AutoGen: Automating Large Language Model Workflows
AutoGen, an innovative framework aimed at simplifying and automating large language model (LLM) workflows, is making headlines in the field of artificial intelligence. Developed by a community of contributors from various backgrounds, including academia and industry, AutoGen promises to revolutionize…