Researcher Jindong Wang and Associate Professor Steven Euijong Whang explore the NeurIPS 2024 work ERBench. ERBench leverages relational databases to create LLM benchmarks that can verify model rationale via keywords as well as check answer correctness. https://lnkd.in/g4vq8KcQ
Microsoft Research
Think Tanks
Redmond, Washington 300,038 followers
We advance science and technology to benefit humanity.
About us
At Microsoft Research, we accelerate scientific discovery and technology innovation to empower every person and organization on the planet to achieve more. We do this by bringing together the best minds across diverse disciplines and backgrounds to take on the most pressing research challenges for Microsoft and for society. Our Research Lens We consider research directions through the lens of the positive impact we aspire to create with and for customers, communities, and all of society.
- Website
-
http://www.microsoft.com/research
External link for Microsoft Research
- Industry
- Think Tanks
- Company size
- 1,001-5,000 employees
- Headquarters
- Redmond, Washington
- Founded
- 1991
Updates
-
In their 2024 NeurIPS paper on RL under latent dynamics, researchers examine whether existing algorithms designed for simple RL problems can be used to solve more complex RL problems. Dylan Foster discusses the modular approach his team explored. https://lnkd.in/evMd6bRu
-
-
Microsoft Research reposted this
🚀 Phi-4 is here! A small language model that performs as well as (and often better than) large models on certain types of complex reasoning tasks such as math. Useful for us in @MSFTResearch, and available now for all researcher on the Azure AI Foundry! https://aka.ms/phi4blog
-
-
Pranjal Chitale discusses the 2024 NeurIPS work CVQA. Spanning 31 languages & the cultures of 30 countries, this VQA benchmark was created with native speakers & cultural experts to evaluate model performance across diverse linguistic & cultural contexts. https://lnkd.in/euEUfVBJ
-
-
Microsoft Research congratulates the PRISM Alignment Dataset team for their NeurIPS 2024 best paper award in the datasets & benchmarks track. This work was supported in part by Accelerating Foundation Models Research and Azure AI Services. https://aka.ms/AAtqkdw
-
-
In Vancouver for #NeurIPS2024? Join us Thursday @ 1 PM PT in Booth #445 for a LIVE recording of the Microsoft Research Podcast feat. Lidong Zhou and Chris Bishop in conversation with guest host IEEE Spectrum's Eliza Strickland. https://lnkd.in/gPpMqR5G
-
-
In “Abstracts,” VP Weizhu Chen discusses his team’s paper on how distinguishing between useful and “noisy” tokens during pretraining can improve token efficiency and model performance. The work was recognized as a best paper runner-up at NeurIPS 2024. https://lnkd.in/eiWTaDaR
-
-
Explore Microsoft @ #NeurIPS2024 with our AI assistant. Discover the work presented by Microsoft research teams, organized by topic. Gain insights into key trends and trajectories shaping AI research. Discover cutting-edge advances in AI: https://lnkd.in/gxpTV68C
-
-
We’re excited to be a part of #NeurIPS2024! Explore the future of AI with over 100 groundbreaking papers, including oral and spotlight sessions, on reinforcement learning, advanced language model training, and multilingual, culturally inclusive benchmarks: https://msft.it/6041ozPKP
-
-
Microsoft Research and collaborators developed an AI-powered, near-real-time global carbon budget method, reducing the lag in analysis from one year to three months. Learn how it revealed a dramatic decline in the global land carbon sink in 2023: https://lnkd.in/eWqN5zCJ