Related papers: Neural Proto-Language Reconstruction

Transformers have achieved great success in natural language processing. Due to the powerful capability of self-attention mechanism in transformers, researchers develop the vision transformers for a variety of computer vision tasks, such as…

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over…

In recent years, work has gone into developing deep interpretable methods for image classification that clearly attributes a model's output to specific features of the data. One such of these methods is the Prototypical Part Network…

Natural language explanations promise to offer intuitively understandable explanations of a neural network's decision process in complex vision-language tasks, as pursued in recent VL-NLE models. While current models offer impressive…

It has been previously observed that training Variational Recurrent Autoencoders (VRAE) for text generation suffers from serious uninformative latent variables problem. The model would collapse into a plain language model that totally…

We investigate the extent to which modern, neural language models are susceptible to structural priming, the phenomenon whereby the structure of a sentence makes the same structure more probable in a follow-up sentence. We explore how…

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…

It is today acknowledged that neural network language models outperform backoff language models in applications like speech recognition or statistical machine translation. However, training these models on large amounts of data can take…

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

This article surveys convolution-based models including convolutional neural networks (CNNs), Conformers, ResNets, and CRNNs-as speech signal processing models and provide their statistical backgrounds and speech recognition, speaker…

Building scalable vision-language models to learn from diverse, multimodal data remains an open challenge. In this paper, we introduce an Efficient Vision-languagE foundation model, namely EVE, which is one unified multimodal Transformer…

Vision-language-action (VLA) models finetuned from vision-language models (VLMs) hold the promise of leveraging rich pretrained representations to build generalist robots across diverse tasks and environments. However, direct fine-tuning on…

Recent work on the Retrieval-Enhanced Transformer (RETRO) model has shown that off-loading memory from trainable weights to a retrieval database can significantly improve language modeling and match the performance of non-retrieval models…

Large, pre-trained transformer-based language models such as BERT have drastically changed the Natural Language Processing (NLP) field. We present a survey of recent work that uses these large language models to solve NLP tasks via…

Recent research has made impressive progress in single-turn dialogue modelling. In the multi-turn setting, however, current models are still far from satisfactory. One major challenge is the frequently occurred coreference and information…

Recurrent neural networks are convenient and efficient models for language modeling. However, when applied on the level of characters instead of words, they suffer from several problems. In order to successfully model long-term…

Proton radiography is a technique extensively used to resolve magnetic field structures in high energy density plasmas, revealing a whole variety of interesting phenomena such as magnetic reconnection and collisionless shocks found in…

Multimodality Representation Learning, as a technique of learning to embed information from different modalities and their correlations, has achieved remarkable success on a variety of applications, such as Visual Question Answering (VQA),…

In this paper we explore the effect of architectural choices on learning a Variational Autoencoder (VAE) for text generation. In contrast to the previously introduced VAE model for text where both the encoder and decoder are RNNs, we…

Human Activity Recognition (HAR) is a core task in pervasive computing systems, where models must operate under strict computational constraints while remaining robust to heterogeneous and evolving deployment conditions. Recent advances…