Zobrazeno 1 - 10
of 93 897
pro vyhledávání: '"vae"'
Video Variational Autoencoder (VAE) encodes videos into a low-dimensional latent space, becoming a key component of most Latent Video Diffusion Models (LVDMs) to reduce model training costs. However, as the resolution and duration of generated videos
Externí odkaz:
http://arxiv.org/abs/2411.17459
Learning a robust video Variational Autoencoder (VAE) is essential for reducing video redundancy and facilitating efficient video generation. Directly applying image VAEs to individual frames in isolation can result in temporal inconsistencies and su
Externí odkaz:
http://arxiv.org/abs/2412.17805
Autor:
Chen, Hao, Wang, Ze, Li, Xiang, Sun, Ximeng, Chen, Fangyi, Liu, Jiang, Wang, Jindong, Raj, Bhiksha, Liu, Zicheng, Barsoum, Emad
Efficient image tokenization with high compression ratios remains a critical challenge for training generative models. We present SoftVQ-VAE, a continuous image tokenizer that leverages soft categorical posteriors to aggregate multiple codewords into
Externí odkaz:
http://arxiv.org/abs/2412.10958
Generating high-quality speech efficiently remains a key challenge for generative models in speech synthesis. This paper introduces VQalAttent, a lightweight model designed to generate fake speech with tunable performance and interpretability. Levera
Externí odkaz:
http://arxiv.org/abs/2411.14642
Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most of existing video VAEs inflate a pretrained image V
Externí odkaz:
http://arxiv.org/abs/2411.06449
Autor:
Gopal, Achintya
Missing data is a common problem in finance and often requires methods to fill in the gaps, or in other words, imputation. In this work, we focused on the imputation of missing implied volatilities for FX options. Prior work has used variational auto
Externí odkaz:
http://arxiv.org/abs/2411.05998
Autor:
Bölat, Kutay, Tindemans, Simon
Generative modelling of multi-user datasets has become prominent in science and engineering. Generating a data point for a given user requires employing user information, and conventional generative models, including variational autoencoders (VAEs),
Externí odkaz:
http://arxiv.org/abs/2411.03936