This paper explores the imperative need and methodology for developing a...
In real-world traffic scenarios, agents such as pedestrians and car driv...
Perception that involves multi-object detection and tracking, and trajec...
In real-world applications, perfect labels are rarely available, making ...
Skin diseases are among the most prevalent health issues, and accurate
c...
Applications that could benefit from automatic understanding of human-hu...
Spiking neural networks (SNNs) have ultra-low energy consumption and hig...
Existing large language models (LLMs) can only afford fix-sized inputs d...
A miniature robotic blimp, as one type of lighter-than-air aerial vehicl...
Modern neural networks are known to give overconfident prediction for
ou...
This paper discusses the problem of extracting spread spectrum hidden da...
Scientific literature understanding tasks have gained significant attent...
The retrieval model is an indispensable component for real-world
knowled...
Recent works reveal that adversarial augmentation benefits the generaliz...
Learning transferable representation of knowledge graphs (KGs) is challe...
Trajectory prediction for autonomous driving must continuously reason th...
Large language models (LLMs), such as ChatGPT, are able to generate
huma...
Predicting trajectories of pedestrians based on goal information in high...
Safety is critical for autonomous driving, and one aspect of improving s...
Recent deep learning methods have achieved promising results in image sh...
Inductive reasoning is a core component of human intelligence. In the pa...
Deep learning models rely on highly optimized tensor libraries for effic...
We propose a novel open-domain question answering (ODQA) framework for
a...
Given its effectiveness on knowledge-intensive natural language processi...
As an emerging secure learning paradigm in leveraging cross-silo private...
Trajectory prediction has been a long-standing problem in intelligent sy...
We present an efficient bi-encoder framework for named entity recognitio...
In an information-seeking conversation, a user converses with an agent t...
Detecting out-of-distribution (OOD) samples is crucial to the safe deplo...
In this paper, we consider the prediction of the helium concentrations a...
As an emerging secure learning paradigm in leveraging cross-agency priva...
Human conversations can evolve in many different ways, creating challeng...
Human language is grounded on multimodal knowledge including visual know...
Detecting out-of-distribution inputs is critical for safe deployment of
...
With the increasing of model capacity brought by pre-trained language mo...
Entity linking faces significant challenges, such as prolific variations...
Motivation: A perennial challenge for biomedical researchers and clinica...
Most of today's AI systems focus on using self-attention mechanisms and
...
Noisy labels damage the performance of deep networks. For robust learnin...
Most recent progress in natural language understanding (NLU) has been dr...
Although residual connection enables training very deep neural networks,...
Due to its potential for a universal interface over both data and text,
...
Learning the generalizable feature representation is critical for few-sh...
Sharing collective perception messages (CPM) between vehicles is investi...
Task-oriented conversational systems often use dialogue state tracking t...
Information overload is a prevalent challenge in many high-value domains...
With the emergence of large-scale decentralized applications, a scalable...
In this short paper an idea is sketched, how to support drivers of an
au...
Recent image classification algorithms, by learning deep features from
l...
Intersections where vehicles are permitted to turn and interact with
vul...