Ofir Lindenbaum

No Prior, No Leakage: Revisiting Reconstruction Attacks in Trained Neural Networks

Fast and Stable Continual Test-Time Adaptation via Masked Modeling and Momentum-Guided Updates

COPER: Correlation-based Permutations for Multi-View Clustering

Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data

AdaRankGrad: Adaptive Gradient Rank and Moments for Memory-Efficient LLMs Training and Fine-Tuning

Hybrid Autoencoders for Tabular Data: Leveraging Model-Based Augmentation in Low-Label Settings

SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training

Partition First, Embed Later: Laplacian-Based Feature Partitioning for Refined Embedding and Visualization of High-Dimensional Data

Multiple Descents in Unsupervised Auto-Encoders: The Role of Noise, Domain Shift and Anomalies

Supervised Band Selection with a Concrete Layer for Hyperspectral Imagery in Remote Sensing and Autonomous Driving

SpecRaGE: Robust and Generalizable Multi-view Spectral Representation Learning