English
Related papers

Related papers: The Free Transformer

200 papers

We investigate large-scale latent variable models (LVMs) for neural story generation -- an under-explored application for open-domain long text -- with objectives in two threads: generation effectiveness and controllability. LVMs,…

Computation and Language · Computer Science 2021-07-09 Le Fang , Tao Zeng , Chaochun Liu , Liefeng Bo , Wen Dong , Changyou Chen

We study the problem of self-supervised structured representation learning using autoencoders for downstream tasks such as generative modeling. Unlike most methods which rely on matching an arbitrary, relatively unstructured, prior…

Machine Learning · Computer Science 2024-02-16 Felix Leeb , Guilia Lanzillotta , Yashas Annadani , Michel Besserve , Stefan Bauer , Bernhard Schölkopf

We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…

Computation and Language · Computer Science 2018-12-12 Artidoro Pagnoni , Kevin Liu , Shangyan Li

We extend the framework of variational autoencoders to represent transformations explicitly in the latent space. In the family of hierarchical graphical models that emerges, the latent space is populated by higher order objects that are…

Machine Learning · Computer Science 2020-04-24 Giorgio Giannone , Saeed Saremi , Jonathan Masci , Christian Osendorfer

The development of high-dimensional generative models has recently gained a great surge of interest with the introduction of variational auto-encoders and generative adversarial neural networks. Different variants have been proposed where…

Computer Vision and Pattern Recognition · Computer Science 2019-04-18 Mickaël Chen , Ludovic Denoyer , Thierry Artières

This work introduces a Transformer-based image compression system. It has the flexibility to switch between the standard image reconstruction and the denoising reconstruction from a single compressed bitstream. Instead of training separate…

Image and Video Processing · Electrical Eng. & Systems 2024-02-21 Yi-Hsin Chen , Kuan-Wei Ho , Shiau-Rung Tsai , Guan-Hsun Lin , Alessandro Gnutti , Wen-Hsiao Peng , Riccardo Leonardi

Deep generative neural networks have proven effective at both conditional and unconditional modeling of complex data distributions. Conditional generation enables interactive control, but creating new controls often requires expensive…

Machine Learning · Computer Science 2017-12-25 Jesse Engel , Matthew Hoffman , Adam Roberts

We present a conformal prediction method for time series using the Transformer architecture to capture long-memory and long-range dependencies. Specifically, we use the Transformer decoder as a conditional quantile estimator to predict the…

Machine Learning · Computer Science 2024-06-11 Junghwan Lee , Chen Xu , Yao Xie

Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence…

Sound · Computer Science 2022-03-22 Yi-Jen Shih , Shih-Lun Wu , Frank Zalkow , Meinard Müller , Yi-Hsuan Yang

Transformer-based language models have shown to be very powerful for natural language generation (NLG). However, text generation conditioned on some user inputs, such as topics or attributes, is non-trivial. Past approach relies on either…

Computation and Language · Computer Science 2020-11-17 Fan-Keng Sun , Cheng-I Lai

We re-examine the situation entity (SE) classification task with varying amounts of available training data. We exploit a Transformer-based variational autoencoder to encode sentences into a lower dimensional latent space, which is used to…

Computation and Language · Computer Science 2021-09-16 Mehdi Rezaee , Kasra Darvish , Gaoussou Youssouf Kebe , Francis Ferraro

Classifier guidance is a recently introduced method to trade off mode coverage and sample fidelity in conditional diffusion models post training, in the same spirit as low temperature sampling or truncation in other types of generative…

Machine Learning · Computer Science 2022-07-27 Jonathan Ho , Tim Salimans

Learned image compression codecs have recently achieved impressive compression performances surpassing the most efficient image coding architectures. However, most approaches are trained to minimize rate and distortion which often leads to…

Computer Vision and Pattern Recognition · Computer Science 2024-03-06 Daniele Mari , Simone Milani

Disentangled representations, where the higher level data generative factors are reflected in disjoint latent dimensions, offer several benefits such as ease of deriving invariant representations, transferability to other tasks,…

Machine Learning · Computer Science 2018-12-31 Abhishek Kumar , Prasanna Sattigeri , Avinash Balakrishnan

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and…

Machine Learning · Computer Science 2020-12-10 George Zerveas , Srideepika Jayaraman , Dhaval Patel , Anuradha Bhamidipaty , Carsten Eickhoff

Transformer is eminently suitable for auto-regressive image synthesis which predicts discrete value from the past values recursively to make up full image. Especially, combined with vector quantised latent representation, the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-12 Jonghwa Yim , Minjae Kim

We propose a generative model that can infer a distribution for the underlying spatial signal conditioned on sparse samples e.g. plausible images given a few observed pixels. In contrast to sequential autoregressive generative models, our…

Computer Vision and Pattern Recognition · Computer Science 2021-03-30 Shubham Tulsiani , Abhinav Gupta

We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is made possible by the…

Machine Learning · Computer Science 2026-05-14 Akhil Premkumar , Sarah Lucioni

Generating images from semantic visual knowledge is a challenging task, that can be useful to condition the synthesis process in complex, subtle, and unambiguous ways, compared to alternatives such as class labels or text descriptions.…

Computer Vision and Pattern Recognition · Computer Science 2022-07-04 Renato Sortino , Simone Palazzo , Concetto Spampinato

Transformers pretrained via next token prediction learn to factor their world into parts, representing these factors in orthogonal subspaces of the residual stream. We formalize two representational hypotheses: (1) a representation in the…

‹ Prev 1 2 3 10 Next ›