Related papers: Modeling Knowledge Acquisition from Multiple Learn…
Humans can visualize new and unknown concepts from their natural language description, based on their experience and previous knowledge. Insipired by this, we present a way to extend this ability to Vision-Language Models (VLMs), teaching…
Knowledge distillation~(KD) has been proved effective for compressing large-scale pre-trained language models. However, existing methods conduct KD statically, e.g., the student model aligns its output distribution to that of a selected…
Nowadays, to achieve competitive advantage, the industrial companies are considering that success is sustained to great product development. That is to manage the product throughout its entire lifecycle. Achieving this goal requires a tight…
Knowledge tracing is a technique that predicts students' future performance by analyzing their learning process through historical interactions with intelligent educational platforms, enabling a precise evaluation of their knowledge…
Many real-world problems exhibit the coexistence of multiple types of heterogeneity, such as view heterogeneity (i.e., multi-view property) and task heterogeneity (i.e., multi-task property). For example, in an image classification problem…
Generative modeling has recently shown great promise in computer vision, but it has mostly focused on synthesizing visually realistic images. In this paper, motivated by multi-task learning of shareable feature representations, we consider…
Humans ability to transfer knowledge through teaching is one of the essential aspects for human intelligence. A human teacher can track the knowledge of students to customize the teaching on students needs. With the rise of online education…
We present a novel multimodal interpretable VQA model that can answer the question more accurately and generate diverse explanations. Although researchers have proposed several methods that can generate human-readable and fine-grained…
Knowledge embeddings (KE) represent a knowledge graph (KG) by embedding entities and relations into continuous vector spaces. Existing methods are mainly structure-based or description-based. Structure-based methods learn representations…
Large Language Models (LLMs) trained on web-scale text corpora have been shown to capture world knowledge in their parameters. However, the mechanism by which language models store different types of knowledge is poorly understood. In this…
Knowledge distillation transfers knowledge from large teacher models to smaller students for efficient inference. While existing methods primarily focus on distillation strategies, they often overlook the importance of enhancing teacher…
In this paper, we propose a novel approach for solving the Visual Question Answering (VQA) task in autonomous driving by integrating Vision-Language Models (VLMs) with continual learning. In autonomous driving, VQA plays a vital role in…
A graphical multiagent model (GMM) represents a joint distribution over the behavior of a set of agents. One source of knowledge about agents' behavior may come from gametheoretic analysis, as captured by several graphical game…
The information bottleneck principle provides an information-theoretic method for representation learning, by training an encoder to retain all information which is relevant for predicting the label while minimizing the amount of other,…
Humans can learn concepts or recognize items from just a handful of examples, while machines require many more samples to perform the same task. In this paper, we build a computational model to investigate the possibility of this kind of…
Knowledge tracing is the task of predicting a learner's future performance based on the history of the learner's performance. Current knowledge tracing models are built based on an extensive set of data that are collected from multiple…
The predominant approach to Visual Question Answering (VQA) demands that the model represents within its weights all of the information required to answer any question about any image. Learning this information from any real training set…
Knowledge-based Vision Question Answering (KB-VQA) systems address complex visual-grounded questions with knowledge retrieved from external knowledge bases. The tasks of knowledge retrieval and answer generation tasks both necessitate…
In recent years, many explanation methods have been proposed to explain individual classifications of deep neural networks. However, how to leverage the created explanations to improve the learning process has been less explored. As the…
Deep neural models in recent years have been successful in almost every field, including extremely complex problem statements. However, these models are huge in size, with millions (and even billions) of parameters, thus demanding more…