Purpose: To determine if fine-tuned large language models (LLMs) can gen...
Recent generative approaches for multi-hop question answering (QA) utili...
Recent years have witnessed impressive results of pre-trained vision-lan...
Bitcoin-NG is an extensible blockchain protocol based on the same trust ...
Traditional neural machine translation (NMT) systems often fail to trans...
Out-of-distribution (OOD) detection is a critical task for reliable
pred...
Mining attacks allow adversaries to obtain a disproportionate share of t...
Recently, RGB-Thermal based perception has shown significant advances.
T...
Performing accurate localization while maintaining the low-level
communi...
In recent years, monocular depth estimation (MDE) has gained significant...
Clinical imaging databases contain not only medical images but also text...
With the growing use of transformer-based language models in medicine, i...
In this paper, we propose a novel framework dubbed peer learning to deal...
Audio-Visual scene understanding is a challenging problem due to the
uns...
While the NLP community is generally aware of resource disparities among...
It is well known that it is difficult to have a reliable and robust fram...
We study a practical yet hasn't been explored problem: how a drone can
p...
Environmental sound classification (ESC) is a challenging problem due to...
Word translation without parallel corpora has become feasible, rivaling ...
Subword tokenization schemes are the dominant technique used in current ...
Depth completion aims at predicting dense pixel-wise depth from a sparse...
It has been shown that machine translation models usually generate poor
...
Short Term Load Forecast (STLF) is necessary for effective scheduling,
o...
The RGB-Thermal (RGB-T) information for semantic segmentation has been
e...
Much recent progress in task-oriented dialogue (ToD) systems has been dr...
We study a novel problem that tackles learning based sensor scanning in ...
Reproducible benchmarks are crucial in driving progress of machine
trans...
The annotation of domain experts is important for some medical applicati...
We uncover networks from news articles to study cross-sectional stock
re...
Neural machine translation (NMT) is sensitive to domain shift. In this p...
Machine learning has brought striking advances in multilingual natural
l...
This paper studies zero-shot cross-lingual transfer of vision-language
m...
As vision based perception methods are usually built on the normal light...
The core problem of visual multi-robot simultaneous localization and map...
Pre-trained cross-lingual encoders such as mBERT (Devlin et al., 2019) a...
The goal of universal machine translation is to learn to translate betwe...
The COVID-19 pandemic is the worst pandemic to strike the world in over ...
Unsupervised machine translation (MT) has recently achieved impressive
r...
Much recent progress in applications of machine learning models to NLP h...
In this paper, we consider adversarial attacks against a system of monoc...
Neural networks are known to be data hungry and domain sensitive, but it...
Previous storytelling approaches mostly focused on optimizing traditiona...
Popular metrics used for evaluating image captioning systems, such as BL...
Despite impressive empirical successes of neural machine translation (NM...
The recent success of neural machine translation models relies on the
av...
It has been previously noted that neural machine translation (NMT) is ve...
Intelligent personal assistant systems, with either text-based or voice-...
Recently, convolutional neural networks (CNNs) have shown great success ...
In this paper, we describe compare-mt, a tool for holistic analysis and
...
This paper describes the ARIEL-CMU submissions to the Low Resource Human...