74 citations · 231 across the 27 of their papers we have counts for
5 papers · 1 filter
Multiresolution Textual Inversion
Giannis Daras, Alexandros G. Dimakis
We extend Textual Inversion to learn pseudo-words that represent a concept at different resolutions. This allows us to generate images that use the concept with different levels of…
Multitasking Models are Robust to Structural Failure: A Neural Model for Bilingual Cognitive Reserve
Giannis Daras, Negin Raoof, Zoi Gkalitsiou +1
We find a surprising connection between multitask learning and robustness to neuron failures. Our experiments show that bilingual language models retain higher performance under va…
Soft Diffusion: Score Matching for General Corruptions
Giannis Daras, Mauricio Delbracio, Hossein Talebi +2
We define a broader family of corruption processes that generalizes previously known diffusion models. To reverse these general diffusions, we propose a new objective called Soft S…
Score-Guided Intermediate Layer Optimization: Fast Langevin Mixing for Inverse Problems
Giannis Daras, Yuval Dagan, Alexandros G. Dimakis +1
We prove fast mixing and characterize the stationary distribution of the Langevin Algorithm for inverting random weighted DNN generators. This result extends the work of Hand and V…
Discovering the Hidden Vocabulary of DALLE-2
Giannis Daras, Alexandros G. Dimakis
We discover that DALLE-2 seems to have a hidden vocabulary that can be used to generate images with absurd prompts. For example, it seems that \texttt{Apoploe vesrreaitais} means b…