Hyesoo Hong — accepted AI-conference papers

2026

A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models

Wonje Jeung, Sangyeon Yoon, Yoonjun Cho, Dongjae Jeon, Sangwoo Shin, Hyesoo Hong +1

ICLR 2026poster

Diffusion large language models (dLLMs) enable any-order generation, but this flexibility enlarges the attack surface: harmful spans may appear at arbitrary positions, and template-based prefilling attacks such as DIJA bypass response-level refusals. We introduce A2D (Any-Order, Any-Step Defense), a…

Cited by 0 Source ↗code ↗Scholar ↗

2026

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

Sangyeon Yoon, Hyesoo Hong, Wonje Jeung, Albert No

ICLR 2026poster

Machine unlearning aims to remove specific content from trained models while preserving overall performance. However, the phenomenon of benign relearning, in which forgotten information reemerges even from benign fine-tuning data, reveals that existing unlearning methods remain fundamentally fragile…

Cited by 0 Source ↗Scholar ↗