Sign in

Jeremias Sulam

@jsulam.bsky.social
78 followers 138 following 18 posts

Assistant Prof. @ JHU 🇦🇷🇺🇸 Mathematics of Data & Biomedical Data Science jsulam.github.io

PostsRepliesMedia
Jeremias Sulam @jsulam.bsky.social · 19/11/2025
Deadline for CPAL coming up on Dec 5! Submit your best work on Parsimony and Learning and come join us in Tübingen in March! cpal.cc
cpal.cc
Home
Conference on Parsimony and Learning (CPAL) - Addressing the low-dimensional structures in high-dimensional data that prevail in machine learning, signal processing, optimization, and beyond.
100
Jeremias Sulam @jsulam.bsky.social · 18/11/2025
The Biomedical Engineering Department at @JohnsHopkins is hiring! Do you work on data science and machine learning for biomedical problems? Consider applying - deadline for full consideration *Dec 5t* www.bme.jhu.edu/careers-indu...
bme.jhu.edu
Join Hopkins BME - Johns Hopkins Biomedical Engineering
Hopkins BME is not only a great place to learn, it’s also a great place to work. Browse the listing of postdoctoral, research, and faculty openings.
010
Jeremias Sulam @jsulam.bsky.social · 22/07/2025
Check this out 📢 Score-based diffusion models are powerful—but slow to sample. Could there be something better? Drop the scores, use proximals instead! We present Proximal Diffusion Models, providing a faster alternative both in theory* and practice. Here’s how it works 🧵(1/n)
110
Jeremias Sulam @jsulam.bsky.social · 14/03/2025
Awesome to see our cover in @cp-patterns.bsky.social finally out! And kudos go to Zhenzhen Wang for her massive work on biomarker discovery for breast cancer www.cell.com/patterns/ful...
cell.com
Bi-level graph learning unveils prognosis-relevant tumor microenvironment patterns in breast multiplexed digital pathology
BiGraph provides a new approach to risk stratification and biomarker discovery in a wide range of cancers. More generally, it demonstrates the potential of data-driven methods to uncover biologically ...
021
Jeremias Sulam @jsulam.bsky.social · 12/02/2025
Today, on #WomenInScience day, this paper on biomarker discovery for breast cancer, by my amazing student Zhenzhen, has just appeared in @cp-patterns.bsky.social 🎉 Her work shows how to construct fully interpretable biomarkers employing bi-level graph learning! @jhu.edu @hopkinsdsai.bsky.social
021
Jeremias Sulam @jsulam.bsky.social · 13/12/2024
Nice write-up by @JHUCompSci about @JacopoTeneggi's work. Puch-line: interpretability of opaque ML models can be posed as hypothesis tests, for which online (efficient) testing procedures can be derived! www.cs.jhu.edu/news/wanna-b...
cs.jhu.edu
Wanna bet? Testing conceptual importance for more explainable AI
Johns Hopkins researchers used betting strategies to help clarify AI models’ decision-making processes.
010
Jeremias Sulam @jsulam.bsky.social · 11/12/2024
📣 What should *ML explanations* convey, and how does one report these precisely and rigorously? @neuripsconf.bsky.social come check Jacopo Teneggi's work on Testing for Explanations via betting this afternoon! I *bet* you'll like it :) openreview.net/pdf?id=A0HSm... @hopkinsdsai.bsky.social
110
Reposted by Jeremias Sulam
Adam Charles @baselesspursuit.bsky.social · 11/12/2024
NeurIPS paper: Excited for our work (with Iuliia Dmitrieva+Sergey Babkin) on "realSEUDO for real-time calcium imaging analysis" arxiv.org/abs/2405.15701 to be presented tomorrow (Thu 4:30-7:30PM). realSEUDO is a fully on-line method for cell detection and activity estimation that runs at >30Hz.
arxiv.org
realSEUDO for real-time calcium imaging analysis
Closed-loop neuroscience experimentation, where recorded neural activity is used to modify the experiment on-the-fly, is critical for deducing causal connections and optimizing experimental time. A cr...
132