3 papers
cs.AI2026
The Confidence Shortcut: A Reasoning Failure Mode of Masked Diffusion Models
Dueun Kim, Albert No
Masked diffusion language models (MDMs) uniquely support any-order generation, with confidence-based decoding currently serving as the de facto standard inference policy. To optimi…
cs.AI2025
Rainbow Padding: Mitigating Early Termination in Instruction-Tuned Diffusion LLMs
Bumjun Kim, Dongjae Jeon, Dueun Kim +2
Diffusion large language models (dLLMs) have emerged as a promising alternative to autoregressive models, offering flexible generation orders and strong performance on complex reas…
cs.LG2025
Understanding and Mitigating Memorization in Generative Models via Sharpness of Probability Landscapes
Dongjae Jeon, Dueun Kim, Albert No
In this paper, we introduce a geometric framework to analyze memorization in diffusion models through the sharpness of the log probability density. We mathematically justify a prev…