微软研究院博客
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:
This special edition of Research Focus highlights some of the 100+ papers from Microsoft Research that were accepted for publication at NeurIPS 2022 – the thirty-sixth annual Conference on Neural Information Processing Systems. Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey,…
| Mengyu Zhou
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.
| Lei Fang, Junren Li, Zhao Ming, Li Tan, 和 Jian-Guang Lou
Retrosynthesis analysis is a critical task in organic chemistry and central to many important industries. It primarily involves decomposing a target molecule into commercially available molecules step by step. Since synthesis strategies can be quite diverse and strategic, retrosynthesis planning…
| Shilin He, Liqun Li, Xu Zhang, Bo Qiao, Chaoyun Zhang, Yu Kang, Rujia Wang, Qingwei Lin 林庆维, Saravan Rajmohan, 和 Dongmei Zhang
AI-backed virtual assistants face challenges in handling complex data structures. TaskWeaver helps users build assistants that understand diverse domain questions, follow examples, and efficiently execute customizable algorithms on complex data structures.
Microsoft Excel is one of the world’s most important software tools, relied upon by users worldwide to create, understand, model, predict, and collaborate. As the Excel team works to leverage new areas of computer science – advancements in programming languages, NLP,…
In this issue of Research Focus: Optimized exit-augmented models for scalable efficient inference; NeurIPS LLM Efficiency Challenge; LLM-empowered automated data exploration; Boosting cloud efficiency with data-driven decision-making and optimization.
In this issue: Skeleton Posterior-guided OpTimization (SPOT) exhibits potential in various causal discovery tasks; Using visual imagery for an EEG-based brain–computer interface; Developing human-centered AI systems to assist creative professionals.