Related papers: Document Neural Autoregressive Distribution Estima…
Deterministic neural networks (NNs) are increasingly being deployed in safety critical domains, where calibrated, robust, and efficient measures of uncertainty are crucial. In this paper, we propose a novel method for training non-Bayesian…
Although deep neural networks have achieved state-of-the-art performance in various machine learning tasks, adversarial examples, constructed by adding small non-random perturbations to correctly classified inputs, successfully fool highly…
Graph neural networks have recently emerged as a very effective framework for processing graph-structured data. These models have achieved state-of-the-art performance in many tasks. Most graph neural networks can be described in terms of…
Mechanistic network models can capture salient characteristics of empirical networks using a small set of domain-specific, interpretable mechanisms. Yet inference remains challenging because the likelihood is often intractable. We show…
Variational autoencoders (VAEs) have been widely applied for text modeling. In practice, however, they are troubled by two challenges: information underrepresentation and posterior collapse. The former arises as only the last hidden state…
In this paper, we explore a new generative approach for learning visual representations. Our method, DARL, employs a decoder-only Transformer to predict image patches autoregressively. We find that training with Mean Squared Error (MSE)…
In this work, we propose a distributed adaptive observer for a class of nonlinear networked systems inspired by biophysical neural network models. Neural systems learn by adjusting intrinsic and synaptic weights in a distributed fashion,…
Developing efficient numerical algorithms for the solution of high dimensional random Partial Differential Equations (PDEs) has been a challenging task due to the well-known curse of dimensionality. We present a new solution framework for…
Distributed optimization is fundamental to large-scale machine learning and control applications. Among existing methods, the alternating direction method of multipliers (ADMM) has gained popularity due to its strong convergence guarantees…
Neural machine learning models can successfully model language that is similar to their training distribution, but they are highly susceptible to degradation under distribution shift, which occurs in many practical applications when…
Approximating distributions over complicated manifolds, such as natural images, are conceptually attractive. The deep latent variable model, trained using variational autoencoders and generative adversarial networks, is now a key technique…
Extracting key information from documents, such as receipts or invoices, and preserving the interested texts to structured data is crucial in the document-intensive streamline processes of office automation in areas that includes but not…
Variational autoencoders have been widely applied for natural language generation, however, there are two long-standing problems: information under-representation and posterior collapse. The former arises from the fact that only the last…
In this work, we propose \texttt{TimeGrad}, an autoregressive model for multivariate probabilistic time series forecasting which samples from the data distribution at each time step by estimating its gradient. To this end, we use diffusion…
Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…
In this work, a region-based Deep Convolutional Neural Network framework is proposed for document structure learning. The contribution of this work involves efficient training of region based classifiers and effective ensembling for…
We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual…
We introduce Autoregressive Diffusion Models (ARDMs), a model class encompassing and generalizing order-agnostic autoregressive models (Uria et al., 2014) and absorbing discrete diffusion (Austin et al., 2021), which we show are special…
We present prompt distribution learning for effectively adapting a pre-trained vision-language model to address downstream recognition tasks. Our method not only learns low-bias prompts from a few samples but also captures the distribution…
This paper proposes a data-driven method to automatically construct graph-based document representations. Building upon the recent work of Bugue\~no and de Melo (2025), we leverage the dynamic sliding-window attention module to effectively…