215 citations · 474 across the 24 of their papers we have counts for
27 papers
Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses
Gon Buzaglo, Niv Haim, Gilad Yehudai +4
Memorization of training data is an active research area, yet our understanding of the inner workings of neural networks is still in its infancy. Recently, Haim et al. (2022) propo…
The Hidden Language of Diffusion Models
Hila Chefer, Oran Lang, Mor Geva +5
Text-to-image diffusion models have demonstrated an unparalleled ability to generate high-quality, diverse images from a textual prompt. However, the internal representations learn…
Reconstructing Training Data from Multiclass Neural Networks
Gon Buzaglo, Niv Haim, Gilad Yehudai +2
Reconstructing samples from the training set of trained neural networks is a major privacy concern. Haim et al. (2022) recently showed that it is possible to reconstruct training s…
Teaching CLIP to Count to Ten
Roni Paiss, Ariel Ephrat, Omer Tov +4
Large vision-language models (VLMs), such as CLIP, learn rich joint image-text representations, facilitating advances in numerous downstream tasks, including zero-shot classificati…
SinFusion: Training Diffusion Models on a Single Image or Video
Yaniv Nikankin, Niv Haim, Michal Irani
Diffusion models exhibited tremendous progress in image and video generation, exceeding GANs in quality and diversity. However, they are usually trained on very large datasets and…
Imagic: Text-Based Real Image Editing with Diffusion Models
Bahjat Kawar, Shiran Zada, Oran Lang +5
Text-conditioned image editing has recently attracted considerable interest. However, most methods are currently either limited to specific editing types (e.g., object overlay, sty…