Omri Azencot

DiffSDA: Unsupervised Diffusion Sequential Disentanglement Across Modalities

Bridging Efficiency and Safety: Formal Verification of Neural Networks with Early Exits

Training-Free Modality-Agnostic Concept Sliders: Fine-Grained Control via Diffusion Models of Images, Audio, and Video

DiffSDA: A Framework for Unsupervised Diffusion Sequential Disentanglement Across Modalities

Curvature Enhanced Data Augmentation for Regression

One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling

Time Series Generation Under Data Scarcity: A Unified Generative Modeling Approach

Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge

Curvature Enhanced Manifold Sampling

A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking

From Noise to Factors: Diffusion-based Unsupervised Sequential Disentanglement

Beyond Data Scarcity: A Frequency-Driven Framework for Zero-Shot Forecasting