15 papers
VLMs Trace Without Tracking: Diagnosing Failures in Visual Path Following
Hyesoo Hong, Minsoo Kim, Wonje Jeung +3
Vision-language models (VLMs) achieve strong performance on multimodal benchmarks, but may still lack robust control over basic visual operations. We study \textit{line tracing}, w…
Few-Shot Truly Benign DPO Attack for Jailbreaking LLMs
Sangyeon Yoon, Wonje Jeung, Yoonjun Cho +2
Fine-tuning APIs make frontier LLMs easy to customize, but they can also weaken safety alignment during fine-tuning. While prior work shows that benign supervised fine-tuning (SFT)…
Multi-Level Knowledge Distillation and Dynamic Self-Supervised Learning for Continual Learning
Taeheon Kim, San Kim, Minhyuk Seo +3
Class-incremental with repetition (CIR), where previously trained classes repeatedly introduced in future tasks, is a more realistic scenario than the traditional class incremental…
BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
Sangyeon Yoon, Sunkyoung Kim, Hyesoo Hong +5
Large language models (LLMs) increasingly store user preferences in persistent memory to support personalization across interactions. However, in third-party communication settings…
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…
A2D: Any-Order, Any-Step Safety Alignment for Diffusion Language Models
Wonje Jeung, Sangyeon Yoon, Yoonjun Cho +4
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…