Investigating vulnerabilities in LLMs; A novel total-duration-aware (TDA) duration model for text-to-speech (TTS); Generative expert metric system through iterative prompt priming; Integrity protection in 5G fronthaul networks:
Learn what’s next for AI at Research Forum on Sept. 3;  WizardArena simulates human-annotated chatbot games; MInference speeds pre-filling for long-context LLMs via dynamic sparse attention; Reef: Fast succinct non-interactive zero-knowledge regex proofs.
In this issue: RENC makes 5G vRAN servers more energy efficient; CoExplorer uses AI to keep video meetings on track; Automatic bug detection in LLM-powered text-based games; MAIRA-2: Grounded radiology report generation.
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.
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Large language models (LLMs) have shown remarkable performance in generating text similar to that created by people, proving…
In this issue: New research on appropriate reliance on generative AI; Power management opportunities for LLMs in the cloud; LLMLingua-2 improves task-agnostic prompt compression; Enhancing COMET to embrace under-resourced African languages:
In this issue: New research helps COMET embrace African languages; FeatUp improves deep features, a computer vision research cornerstone; LLMs in the Imaginarium: Tool Learning through Simulated Trial and Error; Benchmarking LLMs across languages and more.
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.
Structural Understanding Capabilities is a new benchmark for evaluating and improving LLM comprehension of structured table data. This advance can help LLMs process and analyze data more effectively, broadening their applicability in real-world tasks.
Microsoft’s Orca-Math, a specialized small language model, outperforms much larger models in solving math problems that require multi-step reasoning and shows the potential of using feedback to improve language models. Learn more.
In this issue: CaaSPER: vertical autoscaling algorithm dynamically maintains optimal CPU utilization; Improved scene landmark detection for camera localization runs faster, uses less storage; ESUS simplifies usability questionnaires for technical products and services.
Welcome to Research Focus, a series of blog posts that highlights notable publications, events, code/datasets, new hires and other milestones from across the research community at Microsoft. Join Microsoft Research Forum (opens in new tab) for a continuous exchange of ideas about science and technology…
Meet our community of researchers, learn about exciting research topics, and grow your network
Ongoing conversations at the cutting edge of research
Join us for a continuous exchange of ideas about research in the era of general AI
