Related papers: Latent Space Translation via Semantic Alignment

A large body of recent work has identified transformations in the latent spaces of generative adversarial networks (GANs) that consistently and interpretably transform generated images. But existing techniques for identifying these…

Aligned latent spaces, where meaningful semantic shifts in the input space correspond to a translation in the embedding space, play an important role in the success of downstream tasks such as unsupervised clustering and data imputation. In…

Traditional sentence embedding models encode sentences into vector representations to capture useful properties such as the semantic similarity between sentences. However, in addition to similarity, sentence semantics can also be…

Despite the significant recent progress in deep generative models, the underlying structure of their latent spaces is still poorly understood, thereby making the task of performing semantically meaningful latent traversals an open research…

Neural encoder-decoder models of machine translation have achieved impressive results, while learning linguistic knowledge of both the source and target languages in an implicit end-to-end manner. We propose a framework in which our model…

Latent spaces offer an efficient and effective means of summarizing data while implicitly preserving meta-information through relational encoding. We leverage these meta-embeddings to develop a modality-agnostic, unified encoder. Our method…

We study analogical trajectory transfer, where the goal is to translate motion trajectories in one 3D environment to a semantically analogous location in another. Such a capacity would enable machines to perform analogical spatial…

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Breaking down the structure of long texts into semantically coherent segments makes the texts more readable and supports downstream applications like summarization and retrieval. Starting from an apparent link between text coherence and…

Image-to-image (I2I) translation is usually carried out among discrete domains. However, image domains, often corresponding to a physical value, are usually continuous. In other words, images gradually change with the value, and there…

Transformers have been the dominant architecture for Speech Translation in recent years, achieving significant improvements in translation quality. Since speech signals are longer than their textual counterparts, and due to the quadratic…

Multi-layer models with multiple attention heads per layer provide superior translation quality compared to simpler and shallower models, but determining what source context is most relevant to each target word is more challenging as a…

Feed-forward CNNs trained for image transformation problems rely on loss functions that measure the similarity between the generated image and a target image. Most of the common loss functions assume that these images are spatially aligned…

Real-world geometry and 3D vision tasks are replete with challenging symmetries that defy tractable analytical expression. In this paper, we introduce Neural Isometries, an autoencoder framework which learns to map the observation space to…

The training of topic models for a multilingual environment is a challenging task, requiring the use of sophisticated algorithms, topic-aligned corpora, and manual evaluation. These difficulties are further exacerbated when the developer…

Pretrained language models are long known to be subpar in capturing sentence and document-level semantics. Though heavily investigated, transferring perturbation-based methods from unsupervised visual representation learning to NLP remains…

Recent image-to-image translation works have been transferred from supervised to unsupervised settings due to the expensive cost of capturing or labeling large amounts of paired data. However, current unsupervised methods using the…

The Transformer model has revolutionized Natural Language Processing tasks such as Neural Machine Translation, and many efforts have been made to study the Transformer architecture, which increased its efficiency and accuracy. One potential…

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

This paper reveals that large language models (LLMs), despite being trained solely on textual data, are surprisingly strong encoders for purely visual tasks in the absence of language. Even more intriguingly, this can be achieved by a…