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
Reliability Problem
2026
Geometry-Preserving Robust Neural Reconstruction via Statistical Reweighting
British Machine Vision Conference, 2026
PredLM: A Sparse Large Language Model Decoding Accelerator with Hardware-Efficient Zero-Activation Prediction
IEEE Transactions on Circuits and Systems II: Express Briefs, 2026
Efficient Process Reward Modeling via Contrastive Mutual Information
The 64th Annual Meeting of the Association for Computational Linguistics (Main paper), 2026
Bias Alleviation through Network Pruning for Sparse and Debiased Models
IEEE Transactions on Image Processing, 2026
Beyond Prompts: Preserving Semantics in Diffusion-based Communication
IEEE Wireless Communications Letters, 2026
Operator-aware shadow importance sampling for accurate fidelity estimation
Physical Review A, 2026
2025
Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models
The Thirty-ninth Annual Conference on Neural Information Processing Systems, 2025
Prototype-based Explanation for Semantic Gap Reduction with Distributional Embedding
IEEE Access, 2025
Constructing Fair Latent Space for Intersection of Fairness and Explainability
The Association for the Advancement of Artificial Intelligence, 2025
2024
Mitigating Spurious Correlations via Disagreement Probability
The Thirty-eighth Annual Conference on Neural Information Processing Systems, 2024
Learning Dual Hierarchical Representation for 3D Surface Reconstruction
Asian Conference on Computer Vision, 2024
Group-wise Verifiable Coded Computing under Byzantine Attacks and Stragglers
IEEE Transactions on Information Forensics and Security, 2024
2023
Straggler-Exploiting Fully Private Distributed Matrix Multiplication With Chebyshev Polynomials
IEEE Transactions on Communications, 2023
2022
Hierarchical Group Testing for Byzantine Attack Identification in Distributed Matrix Multiplication
IEEE Journal on Selected Areas in Communications, 2022
2021
Securely Straggler-Exploiting Coded Computation for Distributed Matrix Multiplication
IEEE Access, 2021
Chebyshev Polynomial Codes: Task Entanglement-based Coding for Distributed Matrix Multiplication
Proceedings of the 38th International Conference on Machine Learning, 2021
2020
Squeezed Polynomial Codes: Communication-Efficient Coded Computation in Straggler-Exploiting Distributed Matrix Multiplication
IEEE Access, 2020