High-dimensional generative models have many applications including image compression, multimedia generation, anomaly detection and data completion. State-of-the-art estimators for natural images are autoregressive, decomposing the joint distribution over pixels into a product of conditionals parameterized by a deep neural network, e.g. a convolutional neural network such as the PixelCNN. However, PixelCNNs only model a single decomposition of the joint, and only a single generation order is efficient. For tasks such as image completion, these models are unable to use much of the observed context. To generate data in arbitrary orders, we introduce LMConv: a simple modification to the standard 2D convolution that allows arbitrary masks to be applied to the weights at each location in the image. Using LMConv, we learn an ensemble of distribution estimators that share parameters but differ in generation order, achieving improved performance on whole-image density estimation (2.89 bpd on unconditional CIFAR10), as well as globally coherent image completions. Our code is available at https://ajayjain.github.io/lmconv.
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；IBM Thomas J. Watson Research Center（IBM托马斯·J·沃森研究中心）
Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a naïve fashion where redundant computations are unnecessarily repeated. This results in slow generation, making such models infeasible for production environments. In this work, we describe a method to speed up generation in convolutional autoregressive models. The key idea is to cache hidden states to avoid redundant computation. We apply our fast generatio…
The recently proposed mask-predict decoding algorithm has narrowed the performance gap between semi-autoregressive machine translation models and the traditional left-to-right approach. We introduce a new training method for conditional masked language models, SMART, which mimics the semi-autoregressive behavior of mask-predict, producing training examples that contain model predictions as part of their inputs. Models trained with SMART produce higher-quality translations when using mask-predict decoding, effectively closing the remaining performance gap with fully autoregressive models.
Time Series forecasting (univariate and multivariate) is a problem of high complexity due the different patterns that have to be detected in the input, ranging from high to low frequencies ones. In this paper we propose a new model for timeseries prediction that utilizes convolutional layers for feature extraction, a recurrent encoder and a linear autoregressive component. We motivate the model and we test and compare it against a baseline of widely used existing architectures for univariate and multivariate timeseries. The proposed model appears to outperform the baselines in almost every cas…
Non-autoregressive machine translation models significantly speed up decoding by allowing for parallel prediction of the entire target sequence. However, modeling word order is more challenging due to the lack of autoregressive factors in the model. This difficultly is compounded during training with cross entropy loss, which can highly penalize small shifts in word order. In this paper, we propose aligned cross entropy (AXE) as an alternative loss function for training of non-autoregressive models. AXE uses a differentiable dynamic program to assign loss based on the best possible monotonic a…
Self-Supervised Masked Convolutional Transformer Block for Anomaly Detection
University of Central Florida（中佛罗里达大学）；Aalborg University（奥尔堡大学）；University Politehnica of Bucharest（布加勒斯特理工大学）；University of Bucharest（布加勒斯特大学）；SecurifAI（SecurifAI公司）；Milestone Systems（Milestone Systems公司）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Linköping University（林雪平大学）
Learned image compression research has achieved state-of-the-art compression performance with auto-encoder based neural network architectures, where the image is mapped via convolutional neural networks (CNN) into a latent representation that is quantized and processed again with CNN to obtain the reconstructed image. CNN operate on entire input images. On the other hand, traditional state-of-the-art image and video compression methods process images with a block-by-block processing approach for various reasons. Very recently, work on learned image compression with block based approaches have …
Autoregressive models are among the best performing neural density estimators. We describe an approach for increasing the flexibility of an autoregressive model, based on modelling the random numbers that the model uses internally when generating data. By constructing a stack of autoregressive models, each modelling the random numbers of the next model in the stack, we obtain a type of normalizing flow suitable for density estimation, which we call Masked Autoregressive Flow. This type of flow is closely related to Inverse Autoregressive Flow and is a generalization of Real NVP. Masked Autoreg…
University Politehnica of Bucharest（布加勒斯特理工大学）；MBZ University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Aalborg University（奥尔堡大学）；University of Bucharest（布加勒斯特大学）；SecurifAI（SecurifAI公司）；Milestone Systems（Milestone Systems公司）；Linköping University（林雪平大学）；University of Central Florida（中佛罗里达大学）
Anomaly detection is commonly pursued as a one-class classification problem, where models can only learn from normal training samples, while being evaluated on both normal and abnormal test samples. Among the successful approaches for anomaly detection, a distinguished category of methods relies on predicting masked information (e.g. patches, future frames, etc.) and leveraging the reconstruction error with respect to the masked information as an abnormality score. Different from related methods, we propose to integrate the reconstruction-based functionality into a novel self-supervised predic…
CanvasMAR: Improving Masked Autoregressive Video Prediction With Canvas
Institute for Artificial Intelligence, Peking University, Beijing, China（人工智能研究院，北京大学，北京，中国）；School of Intelligence Science and Technology, Peking University, Beijing, China（智能科学与技术学院，北京大学，北京，中国）；State Key Laboratory of General Artificial Intelligence, Peking University, Beijing, China（通用人工智能国家重点实验室，北京大学，北京，中国）
Flow-based generative models, conceptually attractive due to tractability of both the exact log-likelihood computation and latent-variable inference, and efficiency of both training and sampling, has led to a number of impressive empirical successes and spawned many advanced variants and theoretical investigations. Despite their computational efficiency, the density estimation performance of flow-based generative models significantly falls behind those of state-of-the-art autoregressive models. In this work, we introduce masked convolutional generative flow (MaCow), a simple yet effective arch…
Mechanism Shift During Post-training from Autoregressive to Masked Diffusion Language Models
Graduate School of Data Science, Seoul National University（首尔国立大学数据科学研究生院）；Department of Biosystems & Biomaterials Science and Engineering, Seoul National University（首尔国立大学生物系统与生物材料科学与工程系）
Université de Sherbrooke（舍布鲁克大学）；Google DeepMind（谷歌DeepMind）；University of Edinburgh（爱丁堡大学）
There has been a lot of recent interest in designing neural network models to estimate a distribution from a set of examples. We introduce a simple modification for autoencoder neural networks that yields powerful generative models. Our method masks the autoencoder's parameters to respect autoregressive constraints: each input is reconstructed only from previous inputs in a given ordering. Constrained this way, the autoencoder outputs can be interpreted as a set of conditional probabilities, and their product, the full joint probability. We can also train a single network that can decompose th…
Peking University（北京大学）；Bytedance Inc.（字节跳动公司）；University of Oxford（牛津大学）
We identify and overcome two key obstacles in extending the success of BERT-style pre-training, or the masked image modeling, to convolutional networks (convnets): (i) convolution operation cannot handle irregular, random-masked input images; (ii) the single-scale nature of BERT pre-training is inconsistent with convnet's hierarchical structure. For (i), we treat unmasked pixels as sparse voxels of 3D point clouds and use sparse convolution to encode. This is the first use of sparse convolution for 2D masked modeling. For (ii), we develop a hierarchical decoder to reconstruct images from multi…
We propose a new way of constructing invertible neural networks by combining simple building blocks with a novel set of composition rules. This leads to a rich set of invertible architectures, including those similar to ResNets. Inversion is achieved with a locally convergent iterative procedure that is parallelizable and very fast in practice. Additionally, the determinant of the Jacobian can be computed analytically and efficiently, enabling their generative use as flow models. To demonstrate their flexibility, we show that our invertible neural networks are competitive with ResNets on MNIST…
We present Muse, a text-to-image Transformer model that achieves state-of-the-art image generation performance while being significantly more efficient than diffusion or autoregressive models. Muse is trained on a masked modeling task in discrete token space: given the text embedding extracted from a pre-trained large language model (LLM), Muse is trained to predict randomly masked image tokens. Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autore…
Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an LSTM-based autoregressive language model which uses prefix embeddings (from a pretrained masked language model) via fusion (e.g. concatenation) to obtain a richer context representation for language modelling. We find that fusion helps reliably in lowering the perplexity (16.74 $\rightarrow$ 15.80), which is even preserved after a transfer to a dataset from a dif…
Department of Computer Science, Cornell Tech, NYC, USA（康奈尔科技学院计算机科学系）；Department of Computer Science, Cornell University, Ithaca, USA（康奈尔大学计算机科学系）；School of Computer and Communication Sciences, EPFL Lausanne, Switzerland（洛桑联邦理工学院计算机与通信科学学院）；Department of Computer Science, University of Chicago, Illinois（芝加哥大学计算机科学系）；NVIDIA, Santa Clara, USA（英伟达）
Autoregressive convolutional neural networks (CNNs) have been widely exploited for sequence generation tasks such as audio synthesis, language modeling and neural machine translation. WaveNet is a deep autoregressive CNN composed of several stacked layers of dilated convolution that is used for sequence generation. While WaveNet produces state-of-the art audio generation results, the naive inference implementation is quite slow; it takes a few minutes to generate just one second of audio on a high-end GPU. In this work, we develop the first accelerator platform~\textit{FastWave} for autoregres…
While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and text data by a single model rather than a generation of one fixed modality conditioned on the other modality. In this paper, we explore a unified generative vision-and-language (VL) model that can produce both images and text sequences. Especially, we propose a generative VL transformer based on the non-autoregressive mask prediction, named MAGVLT, and compare it with an autoregressive generative VL transformer (ARGVLT…
IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion Models
Applied AI Institute（应用人工智能研究所）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；CMAP, École Polytechnique（巴黎综合理工学院应用数学中心）；Institute of Foundation Models（基础模型研究所）；LRE, EPITA（EPITA 研究与工程实验室）
We propose a model for hierarchical structured data as an extension to the stochastic temporal convolutional network. The proposed model combines an autoregressive model with a hierarchical variational autoencoder and downsampling to achieve superior computational complexity. We evaluate the proposed model on two different types of sequential data: speech and handwritten text. The results are promising with the proposed model achieving state-of-the-art performance.
