July 29, 2025 (9.05 pm. ET for Asia-USA)

Aravind Kaparthi, Geoffrey Fox, Gary Mazzaferro, Gregor von Laszewski, Luke Profio, Satoshi Iwata, Victor Lu

Aravind Kaparthi https://www.linkedin.com/in/aravind-kaparthi-pmp%C2%AE-csm%C2%AE-sasm%C2%AE-57482514/ Program Director at Infinite Computer Solutions Inc
Luke Profio https://www.linkedin.com/in/profio/ at the University of Texas Austin. Customer-oriented technology professional with 10 years’ experience building and scaling innovative solutions at the intersection of computational neuroscience, biomedical informatics and AI/ML architecture.

MLC Science WG - 2025/07/30 01:56 BST - Notes by Gemini
Aravind Kaparthi and Luke Profio were introduced as new members, sharing their backgrounds and interests in AI/ML technologies. Gregor von Laszewski updated the group on the benchmark catalog and report, detailing the validation of YAML file entries and the generation of a 167-page draft report. Geoffrey Fox and Gregor von Laszewski discussed automating benchmark evaluation using AI tools, while also addressing challenges in full automation and the need for explicit evaluation criteria, which Gary Mazzaferro emphasized.
Gregor’s links
https://github.com/mlcommons-science/benchmark
https://mlcommons-science.github.io/bench
Geoffrey’s Links
Time Series Models Summary Table
Dataset summary COMBINED and talk Community Best Practices for Time Series AI Alliance July 10 24