Related papers: Towards Speeding up Program Repair with Non-Autore…

Non-autoregressive neural machine translation (NAT) predicts the entire target sequence simultaneously and significantly accelerates inference process. However, NAT discards the dependency information in a sentence, and thus inevitably…

Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge. In time series forecasting, the autoregressive…

Modern software development relies on the reuse of code via Application Programming Interfaces (APIs). Such reuse relieves developers from learning and developing established algorithms and data structures anew, enabling them to focus on…

Recently, multiple Automated Program Repair (APR) techniques based on Large Language Models (LLMs) have been proposed to enhance the repair performance. While these techniques mainly focus on the single-line or hunk-level repair, they face…

Non-autoregressive neural machine translation (NART) models suffer from the multi-modality problem which causes translation inconsistency such as token repetition. Most recent approaches have attempted to solve this problem by implicitly…

We propose a multiscale approach to time series autoregression, in which linear regressors for the process in question include features of its own path that live on multiple timescales. We take these multiscale features to be the recent…

This paper presents a new approach to the problem of correcting speech recognition errors by means of post-editing. It consists of using a neural sequence tagger that learns how to correct an ASR (Automatic Speech Recognition) hypothesis…

Due to the unparallelizable nature of the autoregressive factorization, AutoRegressive Translation (ART) models have to generate tokens sequentially during decoding and thus suffer from high inference latency. Non-AutoRegressive Translation…

End-to-end (E2E) models have gained attention in the research field of automatic speech recognition (ASR). Many E2E models proposed so far assume left-to-right autoregressive generation of an output token sequence except for connectionist…

While Autoregressive (AR) Transformer-based Generative Language Models are frequently employed for lookahead tasks, recent research suggests a potential discrepancy in their ability to perform planning tasks that require multi-step…

Retrieval Augmented Generation (RAG) is emerging as a flexible and robust technique to adapt models to private users data without training, to handle credit attribution, and to allow efficient machine unlearning at scale. However, RAG…

A Nonlinear Auto-Regressive with eXogenous inputs (NARX) model can be used to describe time-varying processes; where the output depends on both previous outputs and current/previous external input variables. One limitation of NARX models is…

Software debugging is tedious, time-consuming, and even error-prone by itself. So, various automated debugging techniques have been proposed in the literature to facilitate the debugging process. Automated Program Repair (APR) is one of the…

We revisit the performance of template-based APR to build comprehensive knowledge about the effectiveness of fix patterns, and to highlight the importance of complementary steps such as fault localization or donor code retrieval. To that…

Current time-series forecasting models are primarily based on transformer-style neural networks. These models achieve long-term forecasting mainly by scaling up the model size rather than through genuinely autoregressive (AR) rollout. From…

Post-editing in Automatic Speech Recognition (ASR) entails automatically correcting common and systematic errors produced by the ASR system. The outputs of an ASR system are largely prone to phonetic and spelling errors. In this paper, we…

Learning-based automated vulnerability repair (AVR) techniques that utilize fine-tuned language models have shown promise in generating vulnerability patches. However, questions remain about their ability to repair unseen vulnerabilities.…

Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…

Autoregressive models have been widely used in unsupervised text style transfer. Despite their success, these models still suffer from the content preservation problem that they usually ignore part of the source sentence and generate some…

Recent neural network models for image captioning usually employ an encoder-decoder architecture, where the decoder adopts a recursive sequence decoding way. However, such autoregressive decoding may result in sequential error accumulation…