Krishnaswamylab.org

@krishnaswamylab.bsky.social

We develop AI methods for science, particularly deep learning methods based on data geometry, topology and dynamics systems.

(1/N) Thrilled to share that our paper HiPoNet (High dimensional Point cloud Network) to be presented at NeurIPS 2025! HiPoNet treats an entire high-dimensional point cloud as a datapoint! It captures multi-scale geometry and topology of the cloud perform classification and regression tasks.

Bild

🏆 Best Paper Award & Honorable Mention 🏆 Congratulations to our outstanding authors for their exceptional contributions to LoG 2024! 🎉 📜 Your work inspires the entire graph and geometric ML community!

BildBild

✨EXCITING NEWS! We now have a Bluesky account!! AND registration for the 3rd Learning on Graphs conference is open 😊 It is virtual, free to attend, livestreamed, and recorded 📹 Sign up today! The conference is this coming week 😱 forms.gle/eYiDCopJGUc8...

Screen capture of LoG website. The conference is Nov 26-29, 2024. See our website for more details: https://logconference.org/.

(1/n) Intro...We work on mathematical machine learning and deep learning methods that use dynamics modeling, signal processing, geometry and topology to accelerate scientific discovery from data. Our key focus is representation learning of complex unlabelled data, a host of downstream tasks: