429 citations · 1.3k across the 24 of their papers we have counts for
7 papers · 1 filter
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning
Lili Yu, Bowen Shi, Ramakanth Pasunuru +24
We present CM3Leon (pronounced "Chameleon"), a retrieval-augmented, token-based, decoder-only multi-modal language model capable of generating and infilling both text and images. C…
Live Face De-Identification in Video
Oran Gafni, Lior Wolf, Yaniv Taigman
We propose a method for face de-identification that enables fully automatic video modification at high frame rates. The goal is to maximally decorrelate the identity, while having…
Vid2Game: Controllable Characters Extracted from Real-World Videos
Oran Gafni, Lior Wolf, Yaniv Taigman
We are given a video of a person performing a certain activity, from which we extract a controllable model. The model generates novel image sequences of that person, according to a…
Visual Analogies between Atari Games for Studying Transfer Learning in RL
Doron Sobol, Lior Wolf, Yaniv Taigman
In this work, we ask the following question: Can visual analogies, learned in an unsupervised way, be used in order to transfer knowledge between pairs of games and even play one g…
Fitting New Speakers Based on a Short Untranscribed Sample
Eliya Nachmani, Adam Polyak, Yaniv Taigman +1
Learning-based Text To Speech systems have the potential to generalize from one speaker to the next and thus require a relatively short sample of any new voice. However, this promi…
VoiceLoop: Voice Fitting and Synthesis via a Phonological Loop
Yaniv Taigman, Lior Wolf, Adam Polyak +1
We present a new neural text to speech (TTS) method that is able to transform text to speech in voices that are sampled in the wild. Unlike other systems, our solution is able to d…
Multi-GPU Training of ConvNets
Omry Yadan, Keith Adams, Yaniv Taigman +1
In this work we evaluate different approaches to parallelize computation of convolutional neural networks across several GPUs.