Related papers: Learning Multiscale Transformer Models for Sequenc…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Multi-label classification is an important yet challenging task in natural language processing. It is more complex than single-label classification in that the labels tend to be correlated. Existing methods tend to ignore the correlations…

Neural Machine Translation (NMT) models generally perform translation using a fixed-size lexical vocabulary, which is an important bottleneck on their generalization capability and overall translation quality. The standard approach to…

Preference-conditioned image generation seeks to adapt generative models to individual users, producing outputs that reflect personal aesthetic choices beyond the given textual prompt. Despite recent progress, existing approaches either…

Statistical machine translation models have made great progress in improving the translation quality. However, the existing models predict the target translation with only the source- and target-side local context information. In practice,…

Many works proposed methods to improve the performance of Neural Machine Translation (NMT) models in a domain/multi-domain adaptation scenario. However, an understanding of how NMT baselines represent text domain information internally is…

While attention has been empirically shown to improve model performance, it lacks a rigorous mathematical justification. This short paper establishes a novel connection between attention mechanisms and multinomial regression. Specifically,…

We propose the autofocus convolutional layer for semantic segmentation with the objective of enhancing the capabilities of neural networks for multi-scale processing. Autofocus layers adaptively change the size of the effective receptive…

Tokenization is a fundamental step in natural language processing, breaking text into units that computational models can process. While learned subword tokenizers have become the de-facto standard, they present challenges such as large…

Image generation has been successfully cast as an autoregressive sequence generation or transformation problem. Recent work has shown that self-attention is an effective way of modeling textual sequences. In this work, we generalize a…

Transformers excel at discovering patterns in sequential data, yet their fundamental limitations and learning mechanisms remain crucial topics of investigation. In this paper, we study the ability of Transformers to learn pseudo-random…

Recently, multi-instrument music generation has become a hot topic. Different from single-instrument generation, multi-instrument generation needs to consider inter-track harmony besides intra-track coherence. This is usually achieved by…

Large Language Models (LLMs) have demonstrated impressive performance on a wide range of natural language processing (NLP) tasks, primarily through in-context learning (ICL). In ICL, the LLM is provided with examples that represent a given…

Speech foundation models trained with self-supervised learning produce generic speech representations that support a wide range of speech processing tasks. When further adapted with supervised learning, these models can achieve strong…

Organic synthesis is one of the key stumbling blocks in medicinal chemistry. A necessary yet unsolved step in planning synthesis is solving the forward problem: given reactants and reagents, predict the products. Similar to other work, we…

Recurrent neural networks (RNNs) sequentially process data by updating their state with each new data point, and have long been the de facto choice for sequence modeling tasks. However, their inherently sequential computation makes them…

Data augmentation methods for Natural Language Processing tasks are explored in recent years, however they are limited and it is hard to capture the diversity on sentence level. Besides, it is not always possible to perform data…

Diffusion models have gained tremendous success in text-to-image generation, yet still lag behind with visual understanding tasks, an area dominated by autoregressive vision-language models. We propose a large-scale and fully end-to-end…

Attention layers are widely used in natural language processing (NLP) and are beginning to influence computer vision architectures. Training very large transformer models allowed significant improvement in both fields, but once trained,…

Modeling the parser state is key to good performance in transition-based parsing. Recurrent Neural Networks considerably improved the performance of transition-based systems by modelling the global state, e.g. stack-LSTM parsers, or local…