most citedCryoLVM: Self-supervised Learning from Cryo-EM Density Maps with Large Vision Models

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

3 papers · 1 filter

cs.CV2026

Unified Response Geometry for Structured Pruning

Kaixiang Shu

Structured pruning is commonly formulated as ranking individual channels, although channel responses can be complementary or cancel through downstream mixing. Motivated by these re…

cs.CV2026

Adjoint Inversion Reveals Holographic Superposition and Destructive Interference in CNN Classifiers

Kaixiang Shu

How do CNN channels combine scene information into a class-specific response? We develop an input-conditioned adjoint inversion framework that renders individual channels and their…

cs.CV2025

Spatial Information Bottleneck for Interpretable Visual Recognition

Kaixiang Shu, Kai Meng, Junqin Luo

Deep neural networks typically learn spatially entangled representations that conflate discriminative foreground features with spurious background correlations, thereby undermining…