Robustness has been extensively studied in reinforcement learning (RL) t...
This paper presents a comprehensive benchmarking suite tailored to offli...
The prominence of embodied Artificial Intelligence (AI), which empowers
...
Large Language models (LLMs) have shown remarkable success in assisting ...
Multimodal summarization with multimodal output (MSMO) has emerged as a
...
Recently, reward-conditioned reinforcement learning (RCRL) has gained
po...
Decision Transformers (DT) have demonstrated strong performances in offl...
Self-supervised learning is crucial for clinical imaging applications, g...
Continued improvements in machine learning techniques offer exciting new...
In this work, we first formulate the problem of goal-conditioned robotic...
Safe reinforcement learning (RL) trains a constraint satisfaction policy...
We propose to study and promote the robustness of a model as per its
per...
Active perception describes a broad class of techniques that couple plan...
Recent advancements in Large Language Models (LLMs) have drawn increasin...
Multimodal image-text models have shown remarkable performance in the pa...
Continual reinforcement learning (RL) aims to learn a sequence of tasks ...
One key challenge for multi-task Reinforcement learning (RL) in practice...
Curriculum Reinforcement Learning (CRL) aims to create a sequence of tas...
Livestream videos have become a significant part of online learning, whe...
Multimedia summarization with multimodal output (MSMO) is a recently exp...
A vast literature shows that the learning-based visual perception model ...
A trustworthy reinforcement learning algorithm should be competent in so...
Automatic Speech Recognition models require large amount of speech data ...
Recent advances in machine learning have enabled its wide application in...
Electroencephalography (EEG) and language have been widely explored
inde...
There has been an increased interest in applying deep neural networks to...
As a pivotal component to attaining generalizable solutions in human
int...
Humans can leverage prior experience and learn novel tasks from a handfu...
As shown by recent studies, machine intelligence-enabled systems are
vul...
Safe reinforcement learning (RL) trains a policy to maximize the task re...
Self-driving vehicles have their own intelligence to drive on open roads...
In this paper, we propose a dynamic cascaded encoder Automatic Speech
Re...
Multimedia summarization with multimodal output can play an essential ro...
Evaluating the performance of autonomous vehicles (AV) and their complex...
Heart rate variability (HRV) is a practical and noninvasive measure of
a...
Robust Reinforcement Learning (RL) focuses on improving performances und...
Autonomous driving systems have witnessed a significant development duri...
Safe reinforcement learning (RL) aims to learn policies that satisfy cer...
In this paper, we focus on a new method of data augmentation to solve th...
Rare-event simulation techniques, such as importance sampling (IS),
cons...
Goal-directed generation, aiming for solving downstream tasks by generat...
In rare-event simulation, an importance sampling (IS) estimator is regar...
The evaluation of rare but high-stakes events remains one of the main
di...
We present the first framework of Certifying Robust Policies for
reinfor...
Deep Generative Models (DGMs) are known for their superior capability in...
Recent years have witnessed an increasing interest in improving the
perc...
In this paper, we introduce a streaming keyphrase detection system that ...
Optimal transport (OT) has generated much recent interest by its capabil...
Safety is a critical concern when deploying reinforcement learning agent...
This paper studies the safe reinforcement learning (RL) problem without
...