• About
  • Team
  • Publications
  • Research Projects
  • Members' Activities
  • Contact

Conference Presentations

Showcasing our research and innovations at international and domestic conferences - Sharing knowledge and building academic networks worldwide

International Conferences

International
FITAT 2025
17th International Conference on Frontiers of Information Technology, Applications and Tools
Ho Chi Minh City, Vietnam

The Role of Continuous Integration and Continuous Deployment in Modern DevOps Practices

FITAT 2025 - 17th International Conference on Frontiers of Information Technology, Applications and Tools
2025
Rotanakkosal Chhun, Vungsovanreach Kong, Sokheang Chan, Naro Vorn, Tae-Kyung Kim

This paper explores the critical role of Continuous Integration and Continuous Deployment (CI/CD) practices in modern DevOps workflows, examining how these methodologies enhance software development efficiency and reliability.

Slides Paper Conference Site
International
AQIS 2024
24th Asian Quantum Information Science Conference
Sapporo, Japan

Efficient Transpilation of Quantum Circuits to Quantum Intermediate Representation

24th Asian Quantum Information Science Conference (AQIS 2024)
August 2024
Sengthai Heng, Nagyeong Choi, Kimchhor Chiv, Youngsun Han

This paper presents efficient methods for transpiling quantum circuits to Quantum Intermediate Representation (QIR), enabling better interoperability and optimization of quantum programs across different quantum computing platforms.

Conference Site

Domestic Conferences

Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

Order-Conditioned Message Passing over Shape Codes for Amodal Segmentation

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Vungsovanreach Kong, Saravit Soeng, Rotanakkosal Chhun, Tae-Kyung Kim

A single compact network handles two tasks the literature usually splits across two networks: completing the hidden portion of an occluded object's mask (amodal segmentation) and predicting which object is in front of which (pairwise occlusion ordering). Every visible mask is compressed into a 64-dimensional shape code, those codes exchange information through a relational graph whose edges carry a learned three-way occlusion-order distribution, and the updated code is decoded back into a completed mask. The same edges deliver the ordering.

Conference Site
Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

A Verification Agent Harness for Enhancing Factual Reliability in Enterprise RAG Systems

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Saravit Soeng, Vungsovanreach Kong, Sokheang Chan, Tae-Kyung Kim

The proposed research uses multiple verification stages to check generated responses before they are returned to users. Unlike traditional RAG systems that directly provide generated answers, the proposed system includes verification agents that examine whether the responses are supported by evidence, free from contradictions, and factually consistent, and that establish reliability through confidence scoring.

Conference Site
Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

From AI Policy Principles to Monitoring Dashboard: A Conceptual Governance Framework for AI Policy Implementation in Government

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Ratanaktepi Chhor, Naro Vorn, Kimchhor Chiv, Tae-Kyung Kim

This paper proposes a conceptual data-governance framework that turns national AI policy principles and strategies into measurable indicators, and visualizes them through a prototype monitoring dashboard.

Conference Site
Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

Constraint-Aware Constrained Quadratic Modeling for Hyperparameter Tuning

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Kimchhor Chiv, Sokheang Chan, Rotanakkosal Chhun, Tae-Kyung Kim

This study analyzes constraint-aware constrained quadratic modeling (CQM) for hyperparameter tuning as search-space breadth increases. With eight hyperparameters fixed, candidate values per hyperparameter grow from 6 to 128, expanding the space from 68 to 1288 configurations. Experiments compare D-Wave's hybrid CQM solver with greedy, tabu, and SCIP methods.

Conference Site
Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

Grounding Aware Dense GRPO with Selective Sample Replay for Small Text-to-SQL Models

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Sokheang Chan, Kimchhor Chiv, Anand Nayyar, Tae-Kyung Kim

A two-stage SFT and RL framework with GRPO for small-model Text-to-SQL. The SFT stage teaches the model to generate, diagnose, and repair SQL using correct and incorrect teacher traces. The GRPO stage then improves the model with rewards for execution correctness, schema consistency, SQL validity, and repair quality. This produces stronger small language models with fewer SQL errors and more stable RL training.

Conference Site
Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

Motion-Aware Open-Vocabulary Video Object Segmentation

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Rotanakkosal Chhun, Vungsovanreach Kong, Naro Vorn, Ratanaktepi Chhor, Tae-Kyung Kim

This work focuses on finding and segmenting objects in videos based on text descriptions of how they move, for example “the person walking toward the camera” or “the car that brakes”.

Conference Site
Domestic
BIGDAS 2026
The 14th International Conference on Big Data Applications and Services
Jeju Island, South Korea

Multi-Agent Scientific Hypothesis Generation & Verification

BIGDAS 2026 (The 14th International Conference on Big Data Applications and Services), organized by the Korea Big Data Services Society and Chungbuk National University
August 12-14, 2026
Jeju Island, South Korea
Naro Vorn, Ratanaktepi Chhor, Saravit Soeng, Tae-Kyung Kim

Current AI scientist systems such as Google Co-Scientist and Sakana AI Scientist can generate hypotheses and write research papers, but their verification happens inside the same pipeline that generated the idea, causing bias and overconfidence in incorrect results. As evidence, state-of-the-art models detect only 18.4% of errors on the SPOT benchmark. This research explores a reliability-aware multi-agent framework that separates generation from verification through independent verifier, adversarial reviewer, and replication agents, to improve the trustworthiness and reproducibility of AI-generated scientific research.

Conference Site
Domestic
KICS 2024
Korean Institute of Communications and Information Sciences Fall Conference
South Korea

Using Zero-Noise Extrapolation to Improve Variational Quantum Eigensolver for Portfolio Optimization

KICS Fall Conference 2024 (한국통신학회 추계학술대회)
November 2024
South Korea
Kimchhor Chiv, Chansreynich Huot, Myeongseong Go, Youngsun Han

This paper investigates the application of Zero-Noise Extrapolation techniques to enhance the performance of Variational Quantum Eigensolver algorithms for portfolio optimization problems in quantum computing.

Conference Site

© 2026 AICLab - AI Convergence Lab. All rights reserved.