collaborators

10 papers

cs.CL2026

Answer First, Reason Later: When Commitment Order Costs Accuracy in Diffusion Language Models

Jewon Yeom, Jaewon Sok, Seonghyeon Park +3

Masked diffusion language models revise many masked output positions in parallel. We call a token committed once it becomes visible and is never masked again, and call a response a…

cs.LG2026

Stable On-Policy Distillation through Adaptive Target Reformulation

Ijun Jang, Jewon Yeom, Juan Yeo +2

Knowledge distillation (KD) is a widely adopted technique for transferring knowledge from large language models to smaller student models; however, conventional supervised KD often…

cs.AI2026

Inference-Time Vulnerability Beyond Shallow Safety: Alignment Along Generation Trajectories

Kyungmin Park, Taesup Kim

Safety-aligned Large Language Models (LLMs) remain vulnerable to interventions during inference that redirect generation toward harmful outputs. Recent work attributes this to shal…

cs.CL2026

Hallucination as Commitment Failure: Larger LLMs Misfire Despite Knowing the Answer

Jewon Yeom, Jaewon Sok, Heejun Kim +3

Hallucination is often viewed as a direct consequence of missing knowledge: a model answers incorrectly when the correct answer is absent from its generation-time distribution, and…

cs.AI2026

From Noise to Diversity: Random Embedding Injection in LLM Reasoning

Heejun Kim, Seungpil Lee, Jewon Yeom +5

Recent soft prompt research has tried to improve reasoning by inserting trained vectors into LLM inputs, yet whether the gain comes from the learned content or from the act of inje…

cs.CV2026

Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection

Yewon Han, Yumin Seol, EunGyung Kong +2

Existing jailbreak defence frameworks for Large Vision-Language Models often suffer from a safety utility tradeoff, where strengthening safety inadvertently degrades performance on…