Contrastive language-image pre-training (CLIP) has demonstrated remarkab...
Federated Learning (FL) aggregates locally trained models from individua...
In Reinforcement Learning (RL), enhancing sample efficiency is crucial,
...
We consider the problem of recovering hidden communities in the Labeled
...
Respiratory sound contains crucial information for the early diagnosis o...
Transformer-based speech self-supervised learning (SSL) models, such as
...
Although federated learning has made awe-inspiring advances, most studie...
Deep learning in general domains has constantly been extended to
domain-...
The multi-agent multi-armed bandit problem has been studied extensively ...
The multi-agent setting is intricate and unpredictable since the behavio...
Class imbalance problems frequently occur in real-world tasks, and
conve...
Knowledge distillation (KD) is a highly promising method for mitigating ...
Language models (LMs) have demonstrated remarkable performance on downst...
Cell segmentation is a fundamental task for computational biology analys...
The Weather4Cast competition (hosted by NeurIPS 2022) required competito...
Improperly constructed datasets can result in inaccurate inferences. For...
Translation has played a crucial role in improving the performance on
mu...
We investigate the problems of model estimation and reward-free learning...
In this paper, we propose a novel benchmark called the StarCraft Multi-A...
Precipitation forecasting is an important scientific challenge that has
...
Distributional reinforcement learning demonstrates state-of-the-art
perf...
Knowledge Distillation (KD) has recently emerged as a popular method for...
Few-shot class-incremental learning (FSCIL) has addressed challenging
re...
As label noise, one of the most popular distribution shifts, severely
de...
Efficient deployment of deep neural networks across many devices and res...
The performance of deep neural networks is strongly influenced by the
tr...
We study the adversarial bandit problem under S number of switching best...
Most of the recent few-shot learning algorithms are based on transfer
le...
Cross-domain few-shot learning (CD-FSL), where there are few target samp...
Robustness is becoming another important challenge of federated learning...
Neural processes (NPs) aim to stochastically complete unseen data points...
Deep Neural Networks (DNN) have made significant progress in a wide rang...
Cross-domain few-shot learning has drawn increasing attention for handli...
We consider the infinitely many-armed bandit problem with rotting reward...
This paper proposes a novel contrastive learning framework, coined as
Se...
In Federated Learning (FL), a strong global model is collaboratively lea...
Knowledge distillation (KD), transferring knowledge from a cumbersome te...
Modern deep neural networks (DNNs) become frail when the datasets contai...
Motivated by recent developments in designing algorithms based on indivi...
Federated learning has emerged as a new paradigm of collaborative machin...
This paper proposes a theoretical analysis of recommendation systems in ...
Contrastive learning has shown remarkable results in recent self-supervi...
Meta-learning, the effort to solve new tasks with only a few samples, ha...
We study the problem of recovering clusters from binary user feedback. I...
We study the effect of imperfect memory on decision making in the contex...
Given a graphical model (GM), computing its partition function is the mo...
Nowadays, the task of sound source separation is an interesting task for...
We study contextual multi-armed bandit problems under linear realizabili...
We consider the problem of community detection or clustering in the labe...
In this paper, we consider the streaming memory-limited matrix completio...