6 papers · 1 filter
How Representational Priors Shape Generalization in World Action Models
Junha Chun, Youngjoon Jeong, Taesup Kim
World action models (WAMs) are shown to substantially diverge under generalization performance based on their generative backbones. We investigate this gap through the representati…
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…
Learning to Act Robustly with View-Invariant Latent Actions
Youngjoon Jeong, Junha Chun, Taesup Kim
Vision-based robotic policies often struggle with even minor viewpoint changes, underscoring the need for view-invariant visual representations. This challenge becomes more pronoun…
Sparse Imagination for Efficient Visual World Model Planning
Junha Chun, Youngjoon Jeong, Taesup Kim
World model based planning has significantly improved decision-making in complex environments by enabling agents to simulate future states and make informed choices. This computati…