Rhea Chowers

2 accepted papers

2026

Is the Modality Gap a Bug or a Feature? A Robustness Perspective

Rhea Chowers, Oshri Naparstek, Udi Barzelay, Yair Weiss

CVPR 2026

Many modern multi-modal models (e.g. CLIP) seek an embedding space in which the two modalities are aligned. Somewhat surprisingly, almost all existing models show a strong modality gap: the distribution of images is well-separated from the distribution of texts in the shared embedding space. Despite

Cited by 0 Source ↗Scholar ↗

2023

What do CNNs Learn in the First Layer and Why? A Linear Systems Perspective

Rhea Chowers, Yair Weiss

ICML 2023poster

It has previously been reported that the representation that is learned in the first layer of deep Convolutional Neural Networks (CNNs) is highly consistent across initializations and architectures. In this work, we quantify this consistency by considering the first layer as a filter bank and measur…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗