Training large language models (LLMs) with open-domain instruction data ...
Domain generalization (DG) is about learning models that generalize well...
The need to explain the output of a deep neural network classifier is no...
The goal of document-grounded dialogue (DocGD) is to generate a response...
Domain Generalization (DG) is an important open problem in machine learn...
Lifelong learning aims to accumulate knowledge and alleviate catastrophi...
Despite the popularity of Vision Transformers (ViTs) and eXplainable AI
...
In knowledge distillation, a student model is trained with supervisions ...
Overconfidence has been shown to impair generalization and calibration o...
Lifelong learning (LL) is vital for advanced task-oriented dialogue (ToD...
A deep clustering model conceptually consists of a feature extractor tha...
Building models of natural language processing (NLP) is challenging in
l...
Some examples are easier for humans to classify than others. The same sh...
Text style transfer aims to alter the style (e.g., sentiment) of a sente...
Rap generation, which aims to produce lyrics and corresponding singing b...
Personalized conversation models (PCMs) generate responses according to
...
Topic modeling has been one of the most active research areas in machine...
Neural conversation models are known to generate appropriate but
non-inf...
Although deep neural networks generally have fixed network structures, t...
Memory-based collaborative filtering methods like user or item k-nearest...
Implicit feedback is the simplest form of user feedback that can be used...
Matrix factorization is a simple and effective solution to the recommend...
Searching, browsing, and recommendations are common ways in which the "c...
Despite the popularity of deep learning, structure learning for deep mod...
Sparse connectivity is an important factor behind the success of
convolu...
Recently, deep learning based clustering methods are shown superior to
t...
In most probabilistic topic models, a document is viewed as a collection...
Implicit feedback is the simplest form of user feedback that can be used...
We present a novel method for hierarchical topic detection where topics ...
Objective: To treat patients with vascular mild cognitive impairment (VM...
Hierarchical latent tree analysis (HLTA) is recently proposed as a new m...