Related papers: Conditioning Autoencoder Latent Spaces for Real-Ti…
Several recent results in machine learning have established formal connections between autoencoders---artificial neural network models that attempt to reproduce their inputs---and other coding models like sparse coding and K-means. This…
Autoencoders represent an effective approach for computing the underlying factors characterizing datasets of different types. The latent representation of autoencoders have been studied in the context of enabling interpolation between data…
Deep linear networks trained with gradient descent yield low rank solutions, as is typically studied in matrix factorization. In this paper, we take a step further and analyze implicit rank regularization in autoencoders. We show greedy…
Inspired by recent advances in multimodal learning and machine translation, we introduce an encoder-decoder pipeline that learns (a): a multimodal joint embedding space with images and text and (b): a novel language model for decoding…
LLM-based Software Engineering agents face a critical bottleneck: context length limitations cause failures on complex, long-horizon tasks. One promising solution is to encode context as continuous embeddings rather than discrete tokens,…
We introduce a framework for unsupervised learning of structured predictors with overlapping, global features. Each input's latent representation is predicted conditional on the observable data using a feature-rich conditional random field.…
Autoencoder can give rise to an appropriate latent representation of the input data, however, the representation which is solely based on the intrinsic property of the input data, is usually inferior to express some semantic information. A…
Vision Transformer (ViT) based autoencoders often underutilize the global Class token and employ static attention mechanisms, limiting both generative control and optimization efficiency. This paper introduces ViTCAE, a framework that…
Deep learning is playing an instrumental role in the design of the next generation of communication systems. In this letter, we address the massive MIMO interconnect's bandwidth constraint relaxation using autoencoders. The autoencoder is…
Performance optimization is an increasingly challenging but often repetitive task. While each platform has its quirks, the underlying code transformations rely on data movement and computational characteristics that recur across…
Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…
Conformal Autoencoders are a neural network architecture that imposes orthogonality conditions between the gradients of latent variables to obtain disentangled representations of data. In this work we show that orthogonality relations…
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…
In contrast to traditional compression techniques performing linear transforms, the latent space of popular compressive autoencoders is obtained from a learned nonlinear mapping and hard to interpret. In this paper, we explore a promising…
Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or…
We study the problem of learning representations with controllable connectivity properties. This is beneficial in situations when the imposed structure can be leveraged upstream. In particular, we control the connectivity of an…
Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the…
We present work in progress on TimbreCLIP, an audio-text cross modal embedding trained on single instrument notes. We evaluate the models with a cross-modal retrieval task on synth patches. Finally, we demonstrate the application of…
This article introduces a novel and fast method for refining pre-trained static word or, more generally, token embeddings. By incorporating the embeddings of neighboring tokens in text corpora, it continuously updates the representation of…
Latent-space interpolation is commonly used to demonstrate the generalization ability of deep latent variable models. Various algorithms have been proposed to calculate the best trajectory between two encodings in the latent space. In this…