4 papers
Recovering Low-Bit Failures in Vision-Language-Action Policies via Quantization-Conditioned Reinforcement Learning
Seongmin Park, Jaewon Lee, Yujun Heo +4
Quantization lowers deployment costs of vision-language-action (VLA) policies but can compromise task completion. Across five VLA models and 4,050 real-world trials, we systematica…
Erase at the Core: Representation Unlearning for Machine Unlearning
Jaewon Lee, Yongwoo Kim, Donghyun Kim
Many approximate machine unlearning methods demonstrate strong logit-level forgetting -- such as near-zero accuracy on the forget set -- yet continue to preserve substantial inform…
Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted Adaptation
Yongwoo Kim, Sungmin Cha, Hyunsoo Kim +2
With the increasing versatility of text-to-image diffusion models, the ability to selectively erase undesirable concepts (e.g., harmful content) has become indispensable. However,…
Self-supervised denoising of visual field data improves detection of glaucoma progression
Sean Wu, Jun Yu Chen, Vahid Mohammadzadeh +6
Perimetric measurements provide insight into a patient's peripheral vision and day-to-day functioning and are the main outcome measure for identifying progression of visual damage…