7 papers
Safety for Whom? Benchmarking Understanding Beyond Refusal in Egocentric Multimodal Assistants
Yewon Han, Jisu Jeon, Suhyun Choi +5
Egocentric multimodal assistants see through the user's eyes and guide what the user does next, so their outputs directly shape physical actions, including those that affect bystan…
Where Predictive Supervision Goes Shapes What VLA Policies Learn
Hanseul Kim, Jewon Yeom, Youngjoon Jeong +2
Future prediction is increasingly used to improve vision-language-action (VLA) policies, based on the premise that anticipating scene evolution encourages representations useful fo…
PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy Learning
Youngjoon Jeong, Jihwan Yu, Minsoo Jo +2
Robot actions vary in both extent and mode: how much change they produce and what kind of change they produce. A latent action space that reflects this structure may make it easier…
Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical Faults
Minsoo Jo, Taeju Kwon, Junha Chun +2
Deploying Vision-Language-Action (VLA) models in real robotic systems requires robustness not only to semantic and perceptual variations, but also to embodiment-side faults that ch…
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…
Angular Gradient Sign Method: Uncovering Vulnerabilities in Hyperbolic Networks
Minsoo Jo, Dongyoon Yang, Taesup Kim
Adversarial examples in neural networks have been extensively studied in Euclidean geometry, but recent advances in \textit{hyperbolic networks} call for a reevaluation of attack s…
CL3DOR: Contrastive Learning for 3D Large Multimodal Models via Odds Ratio on High-Resolution Point Clouds
Keonwoo Kim, Yeongjae Cho, Taebaek Hwang +2
Recent research has demonstrated that Large Language Models (LLMs) are not limited to text-only tasks but can also function as multimodal models across various modalities, includin…