Federated learning is an emerging distributed machine learning method,
e...
The recent advances in the development of Large Language Models (LLMs) l...
Federated learning (FL) addresses data privacy concerns by enabling
coll...
Adaptive optimization has achieved notable success for distributed learn...
Deploying pre-trained transformer models like BERT on downstream tasks i...
Open-domain question answering is a crucial task that often requires
acc...
Embedding models have shown great power in knowledge graph completion (K...
Recently, masked video modeling has been widely explored and significant...
Third-party libraries (TPLs) are extensively utilized by developers to
e...
The main idea of multimodal recommendation is the rational utilization o...
With the rapid popularity of large language models such as ChatGPT and G...
While generative modeling has been ubiquitous in natural language proces...
Large Language Models (LLMs) are popular for their impressive abilities,...
Sharpness aware minimization (SAM) optimizer has been extensively explor...
Many real-world offline reinforcement learning (RL) problems involve
con...
Data is the foundation of most science. Unfortunately, sharing data can ...
With the development of artificial intelligence, dialogue systems have b...
We present a progressive 3D registration framework that is a highly-effi...
Rather than regressing gaze direction directly from images, we show that...
Due to the lack of human resources for mental health support, there is a...
Knowledge distillation is often used to transfer knowledge from a strong...
LiDAR and camera are two essential sensors for 3D object detection in
au...
Clustering analysis of sequence data continues to address many applicati...
Large pretrained language models can easily produce toxic or biased cont...
Masked Autoencoders (MAE) have been prevailing paradigms for large-scale...
Nonlinear dynamics are ubiquitous in science and engineering application...
Multimodal sentiment analysis and depression estimation are two importan...
With the vigorous development of artificial intelligence (AI), the
intel...
Uncertainty quantification (UQ) is essential for creating trustworthy ma...
Current state-of-the-art document retrieval solutions mainly follow an
i...
Although recent advances in deep learning (DL) have shown a great promis...
Vector quantization (VQ) based ANN indexes, such as Inverted File System...
Large-scale pre-training has shown remarkable performance in building
op...
The effectiveness of knowledge graph embedding (KGE) largely depends on ...
Embedding based retrieval (EBR) is a fundamental building block in many ...
Offensive language detection and prevention becomes increasing critical ...
Ad-hoc search calls for the selection of appropriate answers from a
mass...
Although it is well known that exploration plays a key role in Reinforce...
In this paper, we propose a method for generating a hierarchical, volume...
Transformers have achieved remarkable performance in a myriad of fields
...
Dialogue safety problems severely limit the real-world deployment of neu...
User-item interactions in recommendations can be naturally de-noted as a...
Although pre-trained language models have remarkably enhanced the genera...
Impact mitigation is crucial to the stable locomotion of legged robots,
...
A classical branch of graph algorithms is graph transversals, where one ...
Safe exploration is crucial for the real-world application of reinforcem...
Great research interests have been attracted to devise AI services that ...
Sponsored search ads appear next to search results when people look for
...
In this paper, we consider a prototypical convex optimization problem wi...
In this paper, we develop a symmetric accelerated stochastic Alternating...