Jekyll2026-03-31T21:38:58-07:00https://dcmaddix.github.io/feed.xmlDanielle Maddix RobinsonSenior Applied Scientist, AWS AI LabsDanielle Maddix Robinsondcmaddix@gmail.comEfficiently serve dozens of fine-tuned models with vLLM on Amazon SageMaker AI and Amazon Bedrock2026-02-25T00:00:00-08:002026-02-25T00:00:00-08:00https://dcmaddix.github.io/posts/blog-post-11See our blog on AWS and on vLLM on our optimizations in vLLM for efficient multi-LoRA on MoE models, e.g., GPT-OSS and Qwen3-MoE.]]>Danielle Maddix Robinsondcmaddix@gmail.comScience in the Age of Foundation Models2025-09-26T00:00:00-07:002025-09-26T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-10Featured perspective piece on how foundation models can be beneficial in scientific domains and their current limitations.]]>Danielle Maddix Robinsondcmaddix@gmail.comMitra: Mixed synthetic priors for enhancing tabular foundation models2025-07-22T00:00:00-07:002025-07-22T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-9Featured blog by Amazon Science on our tabular foundation model Mitra, which is trained purely on synthetic data and obtains state-of-the-art performance on classification and regression tasks. Mitra is available in AutoGluon 1.4, and we have also released the weights on HuggingFace. Find the Mitra classifier here and regressor here.]]>Danielle Maddix Robinsondcmaddix@gmail.comPhysics-constrained machine learning for scientific computing2023-05-16T00:00:00-07:002023-05-16T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-8Featured blog by Amazon Science on the research efforts that I am leading on physics-constrained machine learning for scientific computing and computational sciences.]]>Danielle Maddix Robinsondcmaddix@gmail.comA Lasting Legacy in Math and Science2022-06-01T00:00:00-07:002022-06-01T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-5Blog, see pages 6-7 on how my parents inspired my love of math and science.]]>Danielle Maddix Robinsondcmaddix@gmail.comHow applied math impacts forecasting at Amazon2022-04-05T00:00:00-07:002022-04-05T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-3Featured blog by Amazon Science on my research on our award-winning paper on COVID-19 forecasting, where I advised our summer PhD student intern Rui (Ray) Wang.]]>Danielle Maddix Robinsondcmaddix@gmail.comPaper on forecasting spread of COVID-19 wins best-paper award2021-02-22T00:00:00-08:002021-02-22T00:00:00-08:00https://dcmaddix.github.io/posts/blog-post-4Blog on our Best Paper Award at the Machine Learning and Public Health NeurIPS workshop in 2020.]]>Danielle Maddix Robinsondcmaddix@gmail.comCreating neural time series models with Gluon Time Series2019-06-03T00:00:00-07:002019-06-03T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-7Blog on the launch of our open-source library GluonTS for probabilistic time series forecasting.]]>Danielle Maddix Robinsondcmaddix@gmail.comMeeting showcases women in data science2018-03-09T00:00:00-08:002018-03-09T00:00:00-08:00https://dcmaddix.github.io/posts/blog-post-1Blog: Selected interview at the Women in Data Science (WiDS) conference at Stanford University.]]>Danielle Maddix Robinsondcmaddix@gmail.comStanford Engineering Spotlight2016-08-01T00:00:00-07:002016-08-01T00:00:00-07:00https://dcmaddix.github.io/posts/blog-post-2Stanford spotlight on my love of teaching mathematics and MATLAB for Advanced Scientific Computing for the ICME Summer Data Science workshops.]]>Danielle Maddix Robinsondcmaddix@gmail.com