2 papers
cs.LG2026
Understanding Truncated Positional Encodings for Graph Neural Networks
James Flora, Mitchell Black, Weng-Keen Wong +1
Positional encodings (PEs) enhance the power of graph neural networks (GNNs), both theoretically and empirically. Two of the most popular families of PEs - spectral (e.g., Laplacia…
cs.CV2026
LatentDiff: Scaling Semantic Dataset Comparison to Millions of Images
James Flora, Kowshik Thopalli, Akshay R. Kulkarni +2
We present LatentDiff, a scalable framework for semantic dataset comparison that operates directly in the latent space of pretrained vision encoders. By combining sparse autoencode…