My GitHub Projects
Collection of research code and open-source contributions.
Posts by Collection
portfolio
publications
Disentangling Dynamics: A Compositional Framework for Temporal Graph Foundation Models
Published in ICML Workshop on Graph Foundation Models, 2026
TIDES decouples time from space, injecting three frozen, domain-agnostic priors into a static GNN for transferable temporal graph learning. Interactive demo.
Adaptive Memory Retention in Dynamic Graphs
Published in International Conference on Machine Learning (ICML), Spotlight, 2026
We introduce LAMP (Long-range Adaptive Memory Propagation), a differential-equation GNN for snapshot-based dynamic graphs that learns how much information to conserve and how much to dissipate, over space and time. Interactive demo ยท code.
talks
Graphs in Motion: Learning from the Pulse of Dynamical Systems
Published:
I discuss how to improve long range spatio-temporal propagation in dynamic graphs via non-dissipative propagation.
Understanding and Improving Laplacian Positional Encodings for Temporal GNNs
Published:
A seminar presentation on understanding and improving Laplacian positional encodings for temporal GNNs (arXiv:2506.01596).
Dynamic Graphs: The Long-Range Challenge
Published:
Framing GNNs as dynamical systems to study long-range propagation and controlled dissipation in dynamic graphs.
teaching
Teaching experience 1
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Teaching experience 2
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.