Soeun Kim — accepted AI-conference papers

2026

Preserve-Then-Quantize: Balancing Rank Budgets for Quantization Error Reconstruction in LLMs

Yoonjun Cho, Dongjae Jeon, Soeun Kim, Moongyu Jeon, Albert No

ICML 2026poster

Quantization Error Reconstruction (QER) reduces accuracy loss in Post-Training Quantization (PTQ) by approximating weights as $\mathbf{W} \approx \mathbf{Q} + \mathbf{L}\mathbf{R}$, using a rank-$r$ correction to reconstruct quantization error. Prior methods devote the full rank budget to error reco…

Cited by 0 Source ↗Scholar ↗

2025

Assigning Distinct Roles to Quantized and Low-Rank Matrices Toward Optimal Weight Decomposition

Yoonjun Cho, Soeun Kim, Dongjae Jeon, Kyelim Lee, Beomsoo Lee, Albert No

ACL 2025finding

Decomposing weight matrices into quantization and low-rank components ( W≈ Q+LR) is a widely used technique for compressing large language models (LLMs). Existing joint optimization methods iteratively alternate between quantization and low-rank approximation. However, these methods tend to prioriti…

Cited by 0 Source ↗PDF ↗Scholar ↗