ICLR 2026: measuring the hidden geometry of learned representations
Representation holonomy examines how neural features change along input paths, extending analysis beyond pointwise similarity.
Explainable AI
TMLR 2026: prescriptive SVD-inspired attention via spectral energy retention
The paper “Prescriptive SVD-Inspired Attention via Spectral Energy Retention” has been published in Transactions on
AISTATS 2026: process-tensor tomography of SGD and training memory
The paper “Process-Tensor Tomography of SGD: Measuring Non-Markovian Memory via Back-Flow of Distinguishability” was published
IEEE Access 2026: interpretable Vision Transformers via SVDA
“Interpretable Vision Transformers in Image Classification via SVDA” extends the group’s SVD-inspired attention work to
IEEE Access 2025: geometry meets attention through SVD-inspired transformers
The article “Geometry Meets Attention: Interpretable Transformers via SVD Inspiration” was published in IEEE Access