Microsoft Research Special Projects
新闻与深度文章
| Karin Strauss, Bichlien Nguyen, Jake Smith, 和 Sergey Yekhanin
Research manager Karin Strauss and members of the DNA Data Storage Project reflect on the path to developing a synthetic DNA–based system for archival data storage, including the recent open-source release of its most powerful algorithm for DNA error correction.
| Darren Edge, Ha Trinh, Steven Truitt, 和 Jonathan Larson
GraphRAG, a graph-based approach to retrieval-augmented generation (RAG) that significantly improves question-answering over private or previously unseen datasets, is now available on GitHub.
What’s Your Story: Weishung Liu
| Johannes Gehrke 和 Weishung Liu
Principal PM Manager Weishung Liu shares how a career delivering products and customer experiences aligns with her love of people and storytelling and how—despite efforts to defy the expectations that come with growing up in Silicon Valley—she landed in tech.
How can generative AI tools represent less common identities and narratives; Can LLMs help players participate in game narratives; Using LLMs to improve geospatial demographic data; A Graph RAG Approach to Query-Focused Summarization; and more.
| Scott Counts, Jennifer Neville, Mengting Wan, Ryen W. White, 和 Longqi Yang
Microsoft researchers are taking a comprehensive and dynamic approach to help Copilot (web) continuously learn from interaction and feedback, improving the AI system and making it increasingly useful for consumers. Learn more.
Research Focus: Using LLMs in a Rust-based formal verification framework; Rethinking network measurements with user feedback; 3D telemedicine using HoloportationTM communication technology could enhance overseas surgical visits.
| Madeleine Daepp, Alejandro Cuevas, 和 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.
In this edition: A new anonymous token protocol balances fraud detection and privacy; survival instinct in offline RL; Nimble offers rollback protection for confidential cloud services; improved machine learning force fields for molecular dynamics.
RetroRanker mitigates frequency bias in predictions of retrosynthesis models; new algorithm beats PPO on language tasks; DER dataset aids grid planning; improved PPML balances privacy & accuracy across shared data; ASL Citizen boosts sign language modeling.