Our manuscript is available here: arxiv.org/pdf/2108.13407…

Accelerating graph learning apparenthorizons.com/2022/01/22/acc…

Research is in collaboration with Remi Dingreville, Marcin Abrams, Aram Galstyan, and Greg Ver Steeg

New Article: "A Metric Space for Point Process Excitations" by Marmarelis, Ver Steeg and Galstyan jair.org/index.php/jair…

We’ll be presenting our ICLR paper “Improving Mutual Information Estimation using Annealed and Energy-Based Bounds”, Tues @ 10:30am PDT/17:30 GMT Talk: bit.ly/3vcFDW6 Paper: bit.ly/3Kcwi4X w/Sheldon Huang Marzyeh Greg Ver Steeg Roger Grosse Alireza Makhzani

I'm happy to announce that I'm joining Vanderbilt Computer Science this fall as an Assistant Prof, building a Machine Learning and Medical Imaging group (alongside some truly wonderful faculty already there). Please reach out if you want to collab!

Welcome to the official account of the Visual Intelligence and Multimedia Analytics Laboratory (#VIMAL) at USC ISI USC Viterbi School USC. Our research spans theoretical #AI, #ComputerVision, #misinformation #forensics, #deepfake detection and #biometrics.

Pattern formation is key in many physical and biological systems, but it can be hard to discern when transitions occur. We solve this challenge with self-supervised learning and neural nets to detect hierarchies of topological transitions. Details: rdcu.be/cV6q4

**AI can detect new materials** New paper with Marcin Abram, Remi Dingreville, and Greg Ver Steeg just published in NPJ Computational Materials rdcu.be/cV6q4 Slides borrowed from a GREAT talk Remi Dingreville will be presenting at a SIAM DS siammds22.us2.pathable.com/meetings/n9YBP… 🧵1/6

UC in 2023 apparenthorizons.com/2022/12/30/uc-…

AM is a general approach for learning CNFs or SDEs, w/o backdrop thru dynamics in training -natural for trajectory inference in biology, w/time snapshots given -or generative modeling w/flexible endpoint dists or interpolating processes (learned a ton from Kirill Neklyudov here :)

Robnik et al's Micro-canonical Langevin Monte Carlo arxiv.org/pdf/2303.18221… sets a new standard for sampling. Elegant energy preserving dynamics that sample from a target distribution faster and with less bias!

What are the #histopathology image #WSI patterns associated with gene expression in cancer? Can we discover them with #AI and use them for spatial profiling and #precision medicine? Our preprint explores limitations & possibilities of #cpath for this. biorxiv.org/content/10.110…

Congrats to our graduating ISIers! #Classof2023 Hrayr Harutyunyan is earning his #PhD in #ComputerScience, which he obtained under the supervision of his two advisors Aram Galstyan & Greg Ver Steeg. Following graduation, Hrayr will join Google Research in NYC as a #researchscientist!

MI + diffusion! two new papers calculating (pointwise) mutual information as a difference of scores cool experiment by @xxk0ng Greg Ver Steeg identifying areas of an image relevant to changing a prompt arxiv.org/abs/2310.07972 see also Pietro Michiardi arxiv.org/abs/2310.09031

1/8 🚀 AI Breakthrough: "Interpretable Diffusion via Information Decomposition" 🧠 - Quantitative understanding of conditional diffusion models. - Align text-image data using mutual information. - Goes beyond "attention". 🎉 Accepted at #ICLR2024!

Your diffusion model is secretly a noise classifier arxiv.org/abs/2407.08946

✨🧠Excited to have had the opportunity to present our work titled 'Diffusion Bridge Models for 3D Medical Image Translation' in IEEE #embc2025 conference. Some of the important points of discussion from the paper are in this 🧵