collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

DAPD: Dependency-Aware Parallel Decoding via Attention for Diffusion LLMs

Bumjun Kim, Dongjae Jeon, Moongyu Jeon +1

Parallel decoding for Diffusion LLMs (dLLMs) is difficult because each denoising step provides only token-wise marginal distributions, while unmasking multiple tokens simultaneousl…

cs.LG2026

Slower Generalization, Faster Memorization: A Sweet Spot in Algorithmic Learning

Shin So, Kyelim Lee, Albert No

Critical-data-size accounts of grokking suggest a natural post-threshold intuition: once training data is sufficient to identify the underlying rule, additional data should acceler…

cs.LG2026

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

Yoonjun Cho, Dongjae Jeon, Soeun Kim +2

Quantization Error Reconstruction (QER) reduces accuracy loss in Post-Training Quantization (PTQ) by approximating weights as

cs.LG2026

Rethinking Benign Relearning: Syntax as the Hidden Driver of Unlearning Failures

Sangyeon Yoon, Hyesoo Hong, Wonje Jeung +1

Machine unlearning aims to remove specific content from trained models while preserving overall performance. However, the phenomenon of benign relearning, in which forgotten inform…

cs.LG2025

An Information Theoretic Evaluation Metric For Strong Unlearning

Dongjae Jeon, Wonje Jeung, Taeheon Kim +2

Machine unlearning (MU) aims to remove the influence of specific data from trained models, addressing privacy concerns and ensuring compliance with regulations such as the ``right…

cs.LG2025

Information-Theoretic Discrete Diffusion

Moongyu Jeon, Sangwoo Shin, Dongjae Jeon +1

We present an information-theoretic framework for discrete diffusion models that yields principled estimators of log-likelihood using score-matching losses. Inspired by the I-MMSE…