Phill Kyu Rhee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Phill Kyu Rhee has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Minhaz Uddin Ahmed
Inha Univ, Dept Comp Engn, Incheon, South Korea
5 shared publications - Mi Young Nam
Inha University
4 shared publications - Yeong Hyeon Kim
Inha Univ, Dept Comp Engn, Incheon, South Korea
3 shared publications Hak-Chul Shin
2 shared publications- Mi Young Nam
YM-Naeultech
2 shared publications Minhaz Uddin Ahmed
Inha University
2 shared publications
Latest Publications
- Open Access
Moving Beyond Next-Token Prediction: Transformers are Context-Sensitive Language Generators
Large Language Models (LLMs), powered by Transformers, have demonstrated human-like intelligence capabilities, yet their underlying mechanisms remain poorly understood. This paper presents a novel framework for interpreting LLMs as probabilistic left context-sensitive languages (CSLs) generators. We hypothesize that Transformers can be effectively decomposed into three fundamental components: context windows, attention mechanisms, and autoregressive generation frameworks. This decomposition allows for the development of more flexible and interpretable computational models, moving beyond the traditional view of attention and autoregression as inseparable processes. We argue that next-token predictions can be understood as probabilistic, dynamic approximations of left CSL production rules, providing an intuitive explanation for how simple token predictions can yield human-like intelligence outputs. Given that all CSLs are left context-sensitive (Penttonen, 1974), we conclude that Transformers stochastically approximate CSLs, which are widely recognized as models of human-like intelligence. This interpretation bridges the gap between Formal Language Theory and the observed generative power of Transformers, laying a foundation for future advancements in generative AI theory and applications. Our novel perspective on Transformer architectures will foster a deeper understanding of LLMs and their future potentials.
Open AccessMoving Beyond Next-Token Prediction: Transformers are Context-Sensitive Language Generators
Large Language Models (LLMs), powered by Transformers, have demonstrated human-like intelligence capabilities, yet their underlying mechanisms remain poorly understood. This paper presents a novel framework for interpreting LLMs as probabilistic left context-sensitive languages (CSLs) generators. We hypothesize that Transformers can be effectively decomposed into three fundamental components: context windows, attention mechanisms, and autoregressive generation frameworks. This decomposition allows for the development of more flexible and interpretable computational models, moving beyond the traditional view of attention and autoregression as inseparable processes. We argue that next-token predictions can be understood as probabilistic, dynamic approximations of left CSL production rules, providing an intuitive explanation for how simple token predictions can yield human-like intelligence outputs. Given that all CSLs are left context-sensitive (Penttonen, 1974), we conclude that Transformers stochastically approximate CSLs, which are widely recognized as models of human-like intelligence. This interpretation bridges the gap between Formal Language Theory and the observed generative power of Transformers, laying a foundation for future advancements in generative AI theory and applications. Our novel perspective on Transformer architectures will foster a deeper understanding of LLMs and their future potentials.
- 31 December 2020
- Published by Korean Society for Internet Information (KSII) in KSII Transactions on Internet and Information Systems
- Vol. 14 (12) , 4776-4794
EER-ASSL: Combining Rollback Learning and Deep Learning for Rapid Adaptive Object Detection
KSII Transactions on Internet and Information Systems TIIS Paper Details
- 31 December 2020
- Published by Korean Society for Internet Information (KSII) in KSII Transactions on Internet and Information Systems
- Vol. 14 (12) , 4776-4794
EER-ASSL: Combining Rollback Learning and Deep Learning for Rapid Adaptive Object Detection
KSII Transactions on Internet and Information Systems TIIS Paper Details
- Open Access
Combining Obstacle Avoidance and Visual Simultaneous Localization and Mapping for Indoor Navigation
People with disabilities (PWD) face a number of challenges such as obstacle avoidance or taking a minimum path to reach a destination while travelling or taking public transport, especially in airports or bus stations. In some cases, PWD, and specifically visually impaired people, have to wait longer to overcome these situations. In order to solve these problems, the computer-vision community has applied a number of techniques that are nonetheless insufficient to handle these situations. In this paper, we propose a visual simultaneous localization and mapping for moving-person tracking (VSLAMMPT) method that can assist PWD in smooth movement by knowing a position in an unknown environment. We applied expected error reduction with active-semisupervised-learning (EER–ASSL)-based person detection to eliminate noisy samples in dynamic environments. After that, we applied VSLAMMPT for effective smoothing, obstacle avoidance, and uniform navigation in an indoor environment. We analyze the joint approach symmetrically and applied the proposed method to benchmark datasets and obtained impressive performance.
Open AccessCombining Obstacle Avoidance and Visual Simultaneous Localization and Mapping for Indoor Navigation
People with disabilities (PWD) face a number of challenges such as obstacle avoidance or taking a minimum path to reach a destination while travelling or taking public transport, especially in airports or bus stations. In some cases, PWD, and specifically visually impaired people, have to wait longer to overcome these situations. In order to solve these problems, the computer-vision community has applied a number of techniques that are nonetheless insufficient to handle these situations. In this paper, we propose a visual simultaneous localization and mapping for moving-person tracking (VSLAMMPT) method that can assist PWD in smooth movement by knowing a position in an unknown environment. We applied expected error reduction with active-semisupervised-learning (EER–ASSL)-based person detection to eliminate noisy samples in dynamic environments. After that, we applied VSLAMMPT for effective smoothing, obstacle avoidance, and uniform navigation in an indoor environment. We analyze the joint approach symmetrically and applied the proposed method to benchmark datasets and obtained impressive performance.
- 17 December 2019
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (9-10) , 6689-6708
Dynamic MLML-tree based adaptive object detection using heterogeneous data distribution
- 17 December 2019
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 79 (9-10) , 6689-6708
Dynamic MLML-tree based adaptive object detection using heterogeneous data distribution
- Open Access
Hierarchical Open-Set Object Detection in Unseen Data
In this paper, we propose an open-set object detection framework based on a dynamic hierarchical structure with incremental learning capabilities for unseen object classes. We were motivated by the observation that deep features extracted from visual objects show a strong hierarchical clustering property. The hierarchical feature model (HFM) was used to learn a new object class by using collaborative sampling (CS), and open-set-aware active semi-supervised learning (ASSL) algorithms. We divided object proposals into superclasses by using the agglomerative clustering algorithm. Data samples in each superclass node were classified into multiple augmented class nodes instead of directly associating with regular object classes. One or more augmented class nodes are related to a regular object class, and each augmented class has only one superclass. Object proposals from inexperienced data distribution are assigned to an augmented class node. Dynamic HFM nodes in the decision path are assembled to constitute an ensemble prediction, and the new augmented object is associated with a new regular object class. Our experimental results showed that the proposed method uses standard benchmark datasets such as PASCAL VOC, MS COCO, ILSVRC DET, and local datasets to perform better than state-of-the-art techniques.
Open AccessHierarchical Open-Set Object Detection in Unseen Data
In this paper, we propose an open-set object detection framework based on a dynamic hierarchical structure with incremental learning capabilities for unseen object classes. We were motivated by the observation that deep features extracted from visual objects show a strong hierarchical clustering property. The hierarchical feature model (HFM) was used to learn a new object class by using collaborative sampling (CS), and open-set-aware active semi-supervised learning (ASSL) algorithms. We divided object proposals into superclasses by using the agglomerative clustering algorithm. Data samples in each superclass node were classified into multiple augmented class nodes instead of directly associating with regular object classes. One or more augmented class nodes are related to a regular object class, and each augmented class has only one superclass. Object proposals from inexperienced data distribution are assigned to an augmented class node. Dynamic HFM nodes in the decision path are assembled to constitute an ensemble prediction, and the new augmented object is associated with a new regular object class. Our experimental results showed that the proposed method uses standard benchmark datasets such as PASCAL VOC, MS COCO, ILSVRC DET, and local datasets to perform better than state-of-the-art techniques.
- 1 June 2019
- Published by Elsevier in Cognitive Systems Research
- Vol. 55, 257
Corrigendum to “Wild facial expression recognition based on incremental active learning” [Cogn. Syst. Res. 52 (2018) 212–222]
- 1 June 2019
- Published by Elsevier in Cognitive Systems Research
- Vol. 55, 257
Corrigendum to “Wild facial expression recognition based on incremental active learning” [Cogn. Syst. Res. 52 (2018) 212–222]
- 1 September 2016
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 10 (8) , 1503-1510
Efficient object detection using convolutional neural network-based hierarchical feature modeling
- 1 September 2016
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 10 (8) , 1503-1510
Efficient object detection using convolutional neural network-based hierarchical feature modeling
- 19 June 2015
- Published by Springer Nature
- p. 157-166
Robust Facial Feature Localization using Data-Driven Semi-supervised Learning Approach
- 19 June 2015
- Published by Springer Nature
- p. 157-166
Robust Facial Feature Localization using Data-Driven Semi-supervised Learning Approach
- 10 May 2014
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 12 (3) , 628-636
Mouth tracking for hands-free robot control systems
- 10 May 2014
- Published by Springer Nature in International Journal of Control, Automation, and Systems
- Vol. 12 (3) , 628-636
Mouth tracking for hands-free robot control systems
- 30 April 2013
- Published by The Institute of Webcasting, Internet and Telecommunication in The Journal of The Institute of Internet, Broadcasting and Communication
- Vol. 13 (2) , 171-179
Performance Improvement of Eye Tracking System using Reinforcement Learning
- 30 April 2013
- Published by The Institute of Webcasting, Internet and Telecommunication in The Journal of The Institute of Internet, Broadcasting and Communication
- Vol. 13 (2) , 171-179
Performance Improvement of Eye Tracking System using Reinforcement Learning