BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//The Institute for Data-Intensive Engineering and Science - ECPv6.15.14//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:The Institute for Data-Intensive Engineering and Science
X-ORIGINAL-URL:https://www.idies.jhu.edu
X-WR-CALDESC:Events for The Institute for Data-Intensive Engineering and Science
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251111T120000
DTEND;TZID=America/New_York:20251111T133000
DTSTAMP:20260501T002618
CREATED:20251028T165802Z
LAST-MODIFIED:20251110T151312Z
UID:23232-1762862400-1762867800@www.idies.jhu.edu
SUMMARY:IDIES RSE Luncheon Seminar:\nDaniel Muthukrishna
DESCRIPTION:IDIES Luncheon Seminar Series\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nTuesday\, November 11 @ 12:00pm–1:30pm \n\n\n\n| \n\n\n\nBloomberg Center for Physics and Astronomy\, Room 462 \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nSpeaker: \n\n\n\nDaniel Muthukrishna\n\n\n\nMassachusetts Institute of Technology (MIT)\, Harvard’s Center for Astrophysics \n\n\n\n\n\nImage courtesy of Daniel Muthukrishna’s personal site: https://danielmuthukrishna.com/ \n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\nDaniel Muthukrishna\, astrophysicist and ML research scientist at the Massachusetts Institute of Technology (MIT) and an AstroAI Fellow at Harvard & Smithsonian Center for Astrophysics\, visits IDIES at the Bloomberg Center for Physics and Astronomy  on Tuesday\, November 11 at 12pm. Registration is required. \n\n\n\nWith a PhD in Astrophysics from the University of Cambridge\, Dr. Muthukrishna specializes in applying advanced machine learning techniques to analyze astronomical data. He is a vital member of the Transiting Exoplanet Survey Satellite (TESS) team\, where he leverages neural networks to classify exoplanets. \n\n\n\nHis research covers a range of topics\, from modeling supernovae to anomaly detection in large datasets using cutting-edge methods like diffusion models and transformers. Dr. Muthukrishna has developed widely-used software tools that enhance the accuracy and efficiency of astronomical data analysis. \n\n\n\n\n\n\n\n\n\nSpeaking on: \n\n\n\nCausal Foundation Models: Disentangling Physics from Systematics\n\n\n\nRegistrations are closed for this event \n\n\n\n\n\nTalk Abstract: Foundation models for scientific data must contend with a fundamental challenge: observations often conflate the true underlying physical phenomena with systematic distortions introduced by measurement instruments. This entanglement limits model generalization\, especially in heterogeneous or multi-instrument settings.  \n\n\n\nIn this talk\, I  present a causally-motivated foundation model that explicitly disentangles physical and instrumental factors using a dual-encoder architecture trained with structured contrastive learning or a generative flow-matching model. Leveraging naturally occurring observational triplets (i.e.\, where the same target is measured under varying conditions\, and distinct targets are measured under shared conditions)\, the model learns separate latent representations for the underlying physical signal and instrument effects. Evaluated on simulated astronomical time series designed to resemble the complexity of variable stars observed by missions like NASA’s Transiting Exoplanet Survey Satellite (TESS)\, the method outperforms traditional single-latent space foundation models on downstream prediction tasks\, particularly in low-data regimes. These results demonstrate that our model supports key capabilities of foundation models\, including few-shot generalization and efficient adaptation\, and highlight the importance of encoding causal structure into representation learning for structured data.  \n\n\n\nRegistration is free\, but required. A pizza lunch will be provided.
URL:https://www.idies.jhu.edu/event/seminar-muthukrishna/
CATEGORIES:IDIES Seminar
END:VEVENT
END:VCALENDAR