Yong-Guk Kim

Training language models from scratch presents a critical challenge in Natural Language Processing (NLP), primarily due to the computational demands of pre-trained Large Language Models, which are predominantly trained on English corpora using extensive resources. While offering viable solutions, existing alternatives still rely heavily on high-performance hardware. This work introduces a different approach to reducing the algorithmic complexity of Transformer-based architectures through the U-Net Encapsulated Transformer (UET), which applies dimensionality reduction to token embeddings. The UET architecture enables the development of language models with significantly reduced parameter sizes for a given set of hyperparameters. Alternatively, it allows researchers to design models of comparable size but with a substantially greater number of Transformer blocks, enhancing model depth and potential capacity. This study also outlines practical methodologies for training language models in resource-constrained environments. Experimental results illustrate the potential of the UET architecture in achieving reasonable performance under resource-constrained conditions, highlighting its promise as an accessible alternative for language model development. This work could broaden the accessibility of NLP research, empowering researchers with hardware constraints to contribute to language model development.

A 3D avatar typically has one of six cardinal facial expressions. To simulate realistic emotional variation, we should be able to render a facial transition between two arbitrary expressions. This study presents a new framework for instruction-driven facial expression generation that produces a 3D face and, starting from an image of the face, transforms the facial expression from one designated facial expression to another. The Instruction-driven Facial Expression Decomposer (IFED) module is introduced to facilitate multimodal data learning and capture the correlation between textual descriptions and facial expression features. Subsequently, we propose the Instruction to Facial Expression Transition (I2FET) method, which leverages IFED and a vertex reconstruction loss function to refine the semantic comprehension of latent vectors, thus generating a facial expression sequence according to the given instruction. Lastly, we present the Facial Expression Transition model to generate smooth transitions between facial expressions. Extensive evaluation suggests that the proposed model outperforms state-of-the-art methods on the CK+ and CelebV-HQ datasets. The results show that our framework can generate facial expression trajectories according to text instruction. Considering that text prompts allow us to make diverse descriptions of human emotional states, the repertoire of facial expressions and the transitions between them can be expanded greatly. We expect our framework to find various practical applications More information about our project can be found at https://vohoanganh.github.io/tg3dfet/

A 3D avatar typically has one of six cardinal facial expressions. To simulate realistic emotional variation, we should be able to render a facial transition between two arbitrary expressions. This study presents a new framework for instruction-driven facial expression generation that produces a 3D face and, starting from an image of the face, transforms the facial expression from one designated facial expression to another. The Instruction-driven Facial Expression Decomposer (IFED) module is introduced to facilitate multimodal data learning and capture the correlation between textual descriptions and facial expression features. Subsequently, we propose the Instruction to Facial Expression Transition (I2FET) method, which leverages IFED and a vertex reconstruction loss function to refine the semantic comprehension of latent vectors, thus generating a facial expression sequence according to the given instruction. Lastly, we present the Facial Expression Transition model to generate smooth transitions between facial expressions. Extensive evaluation suggests that the proposed model outperforms state-of-the-art methods on the CK+ and CelebV-HQ datasets. The results show that our framework can generate facial expression trajectories according to text instruction. Considering that text prompts allow us to make diverse descriptions of human emotional states, the repertoire of facial expressions and the transitions between them can be expanded greatly. We expect our framework to find various practical applications. More information about our project can be found at https://vohoanganh.github.io/tg3dfet/

Current technological advancements in Information Technology are closely linked to Generative Artificial Intelligence, enabling the automation of complex tasks such as generating documents, images, videos, audio, and actions. As such tasks can save much human labor and resources, diverse industries are trying to adopt this technology. However, developing a product utilizing Generative AI is a challenging task, partly because it is a new technology and many users are not familiar with it yet. This paper’s primary goal is to find a better way to design Generative AI systems, especially from the Human-Computer Interaction perspective. To begin, we propose a taxonomy for Generative AI systems based on their modality, such as text-based, image-based, audio-based, and multi-modal-based systems, and then evaluate them in terms of their usability, because their functionalities should be aligned with the User Interface (UI), leading to a better User Experience (UX). We survey important trends in this area and introduce future applications by touching upon the issue of explainable AI. Although Generative AI has a bright future, it faces formidable challenges in our industries and society. It is hoped that the taxonomy and research findings presented here will be a useful framework for future research in Generative AI systems and their UI/UX.

Object detection and classification in autonomous vehicles are crucial for ensuring safe and efficient navigation through complex environments. This paper addresses the need for robust detection and classification algorithms tailored specifically for Indian roads, which present unique challenges such as diverse traffic patterns, erratic driving behaviors, and varied weather conditions. Despite significant progress in object detection and classification for autonomous vehicles, existing methods often struggle to generalize effectively to the conditions encountered on Indian roads. This paper proposes a novel approach utilizing the YOLOv8 deep learning model, designed to be lightweight, scalable, and efficient for real-time implementation using onboard cameras. Experimental evaluations were conducted using real-life scenarios encompassing diverse weather and traffic conditions. Videos captured in various environments were utilized to assess the model’s performance, with particular emphasis on its accuracy and precision across 35 distinct object classes. The experiments demonstrate a precision of 0.65 for the detection of multiple classes, indicating the model’s efficacy in handling a wide range of objects. Moreover, real-time testing revealed an average accuracy exceeding 70% across all scenarios, with a peak accuracy of 95% achieved in optimal conditions. The parameters considered in the evaluation process encompassed not only traditional metrics but also factors pertinent to Indian road conditions, such as low lighting, occlusions, and unpredictable traffic patterns. The proposed method exhibits superiority over existing approaches by offering a balanced trade-off between model complexity and performance. By leveraging the YOLOv8 architecture, this solution achieved high accuracy while minimizing computational resources, making it well suited for deployment in autonomous vehicles operating on Indian roads.

Recently, machine learning has been very useful in solving diverse tasks with drones, such as autonomous navigation, visual surveillance, communication, disaster management, and agriculture. Among these machine learning, two representative paradigms have been widely utilized in such applications: supervised learning and reinforcement learning. Researchers prefer to use supervised learning, mostly based on convolutional neural networks, because of its robustness and ease of use but yet data labeling is laborious and time-consuming. On the other hand, when traditional reinforcement learning is combined with the deep neural network, it can be a very powerful tool to solve high-dimensional input problems such as image and video. Along with the fast development of reinforcement learning, many researchers utilize reinforcement learning in drone applications, and it often outperforms supervised learning. However, it usually requires the agent to explore the environment on a trial-and-error basis which is high cost and unrealistic in the real environment. Recent advances in simulated environments can allow an agent to learn by itself to overcome these drawbacks, although the gap between the real environment and the simulator has to be minimized in the end. In this sense, a realistic and reliable simulator is essential for reinforcement learning training. This paper investigates various drone simulators that work with diverse reinforcement learning architectures. The characteristics of the reinforcement learning-based drone simulators are analyzed and compared for the researchers who would like to employ them for their projects. Finally, we shed light on some challenges and potential directions for future drone simulators.