Publications

Publication Archive

Selected and recent papers from TML and Prof. Sangwoo Hong.

Research Taxonomy

Publications organized by AI stack layer and, when applicable, a cross-layer reliability problem.

Layer

Reliable ComputingFoundation ModelsPhysical World

Reliability Problem

UnlearningPrivacyRobustnessAlignmentExplainability

2026

Teaser figure for Function-Level Execution Feedback for Code Preference Optimization
EMNLP Findings Foundation Models Alignment

Function-Level Execution Feedback for Code Preference Optimization

Idris Nechnech, Sehwan Kim, Jimin Seo, Yeongoon Kim, Minhae Oh, Sangwoo Hong, Jungwoo Lee

Findings of the Association for Computational Linguistics: EMNLP, 2026

Paper Code
Teaser figure for Geometry-Preserving Robust Neural Reconstruction via Statistical Reweighting
BMVC Physical World Robustness

Geometry-Preserving Robust Neural Reconstruction via Statistical Reweighting

Jiyoon Shin, Sangwoo Hong

British Machine Vision Conference, 2026

Teaser figure for PredLM: A Sparse Large Language Model Decoding Accelerator with Hardware-Efficient Zero-Activation Prediction
TCAS-II Reliable Computing

PredLM: A Sparse Large Language Model Decoding Accelerator with Hardware-Efficient Zero-Activation Prediction

Seunghyun Moon, Seowon Ji, Sangwoo Hong, Eunji Kwon

IEEE Transactions on Circuits and Systems II: Express Briefs, 2026

Paper
Teaser figure for Efficient Process Reward Modeling via Contrastive Mutual Information
ACL Foundation Models Alignment

Efficient Process Reward Modeling via Contrastive Mutual Information

Nakyung Lee, Sangwoo Hong, Jungwoo Lee

The 64th Annual Meeting of the Association for Computational Linguistics (Main paper), 2026

Paper
Teaser figure for Bias Alleviation through Network Pruning for Sparse and Debiased Models
TIP Foundation Models Fairness

Bias Alleviation through Network Pruning for Sparse and Debiased Models

Sangwoo Hong, Sehwan Kim, Hyungjun Joo, Hyeonggeun Han, Jiyoon Shin, Yoav Wald, and Jungwoo Lee

IEEE Transactions on Image Processing, 2026

Paper
Teaser figure for Beyond Prompts: Preserving Semantics in Diffusion-based Communication
WCL Foundation Models

Beyond Prompts: Preserving Semantics in Diffusion-based Communication

Wonjung Kim, Nakyung Lee, Sangwoo Hong*, Jungwoo Lee

IEEE Wireless Communications Letters, 2026

Paper
Teaser figure for MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction
ICML Physical World

MVP-LAM: Learning Action-Centric Latent Action via Cross-Viewpoint Reconstruction

Jung Min Lee, Dohyeok Lee, Seokhun Ju, Taehyun Cho, Jin Woo Koo, Li Zhao, Sangwoo Hong, Jungwoo Lee

Proceedings of the 43rd International Conference on Machine Learning, 2026

Paper Code Project
Teaser figure for An Adaptive Sampling Framework for Diffusion-based Dataset Distillation with High Fidelity and Diversity
AAAI Foundation Models

An Adaptive Sampling Framework for Diffusion-based Dataset Distillation with High Fidelity and Diversity

Sunbeom Jeong, Sehwan Kim, Hyeonggeun Han, Hyungjun Joo, Sangwoo Hong, Jungwoo Lee

40th Annual AAAI Conference on Artificial Intelligence, 2026

Paper Code Oral Presentation
Teaser figure for Operator-aware shadow importance sampling for accurate fidelity estimation
PRA Reliable Computing

Operator-aware shadow importance sampling for accurate fidelity estimation

Hyunho Cha, Sangwoo Hong, Jungwoo Lee

Physical Review A, 2026

Paper

2025

Teaser figure for Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
NeurIPS Foundation Models Privacy

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

Hyeonggeun Han*, Sehwan Kim*, Hyungjun Joo, Sangwoo Hong, Jungwoo Lee

The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025

Paper
Teaser figure for Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition
arXiv Foundation Models Robustness

Mix from Failure: Confusion-Pairing Mixup for Long-Tailed Recognition

Youngseok Yoon, Sangwoo Hong, Hyungjoon Joo, Yao Qin, Haewon Jeong, Jungwoo Lee

arXiv, 2025

Paper Preprint
Teaser figure for Prototype-based Explanation for Semantic Gap Reduction with Distributional Embedding
IEEE Access Foundation Models Explainability

Prototype-based Explanation for Semantic Gap Reduction with Distributional Embedding

Hyungjun Joo, Sangwoo Hong, Hyeonggeun Han, Youngseok Yoon, Jungwoo Lee

IEEE Access, 2025

Paper
Teaser figure for Constructing Fair Latent Space for Intersection of Fairness and Explainability
AAAI Foundation Models FairnessExplainability

Constructing Fair Latent Space for Intersection of Fairness and Explainability

Hyungjun Joo, Hyeonggeun Han, Sehwan Kim, Sangwoo Hong, Jungwoo Lee

The Association for the Advancement of Artificial Intelligence, 2025

Paper

2024

Teaser figure for Mitigating Spurious Correlations via Disagreement Probability
NeurIPS Foundation Models Robustness

Mitigating Spurious Correlations via Disagreement Probability

Hyeonggeun Han, Sehwan Kim, Hyungjun Joo, Sangwoo Hong, Jungwoo Lee

The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024

Paper
Teaser figure for NeRFlex: Flexible Neural Radiance Fields with Diffeomorphic Deformation
IEEE Access Physical World

NeRFlex: Flexible Neural Radiance Fields with Diffeomorphic Deformation

Jiyoon Shin, Sangwoo Hong, Jungwoo Lee

IEEE Access, 2024

Paper
Teaser figure for Learning Dual Hierarchical Representation for 3D Surface Reconstruction
ACCV Physical World

Learning Dual Hierarchical Representation for 3D Surface Reconstruction

Jiyoon Shin, Youngwook Kim, Sangwoo Hong, Jungwoo Lee

Asian Conference on Computer Vision, 2024

Paper
Teaser figure for Group-wise Verifiable Coded Computing under Byzantine Attacks and Stragglers
TIFS Reliable Computing Robustness

Group-wise Verifiable Coded Computing under Byzantine Attacks and Stragglers

Sangwoo Hong, Heecheol Yang, Youngseok Yoon, Jungwoo Lee

IEEE Transactions on Information Forensics and Security, 2024

Paper
Teaser figure for GBMix: Enhancing Fairness by Group-Balanced Mixup
IEEE Access Foundation Models Fairness

GBMix: Enhancing Fairness by Group-Balanced Mixup

Sangwoo Hong, Youngseok Yoon, Hyungjun Joo, Jungwoo Lee

IEEE Access, 2024

Paper

2023

Teaser figure for Straggler-Exploiting Fully Private Distributed Matrix Multiplication With Chebyshev Polynomials
TCOM Reliable Computing Privacy

Straggler-Exploiting Fully Private Distributed Matrix Multiplication With Chebyshev Polynomials

Sangwoo Hong, Heecheol Yang, Youngseok Yoon, Jungwoo Lee

IEEE Transactions on Communications, 2023

Paper

2022

Teaser figure for Hierarchical Group Testing for Byzantine Attack Identification in Distributed Matrix Multiplication
JSAC Reliable Computing Robustness

Hierarchical Group Testing for Byzantine Attack Identification in Distributed Matrix Multiplication

Sangwoo Hong, Heecheol Yang, Jungwoo Lee

IEEE Journal on Selected Areas in Communications, 2022

Paper

2021

Teaser figure for Securely Straggler-Exploiting Coded Computation for Distributed Matrix Multiplication
IEEE Access Reliable Computing Privacy

Securely Straggler-Exploiting Coded Computation for Distributed Matrix Multiplication

Heecheol Yang, Sangwoo Hong, Jungwoo Lee

IEEE Access, 2021

Paper
Teaser figure for Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication
ICML Reliable Computing

Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication

Sangwoo Hong, Heecheol Yang, Youngseok Yoon, Taehyun Cho, Jungwoo Lee

Proceedings of the 38th International Conference on Machine Learning, 2021

Paper Oral Presentation

2020

Teaser figure for Squeezed Polynomial Codes: Communication-Efficient Coded Computation in Straggler-Exploiting Distributed Matrix Multiplication
IEEE Access Reliable Computing

Squeezed Polynomial Codes: Communication-Efficient Coded Computation in Straggler-Exploiting Distributed Matrix Multiplication

Sangwoo Hong, Heecheol Yang, Jungwoo Lee

IEEE Access, 2020

Paper