World-action models (WAMs) have emerged as a promising paradigm for robot manipulation by jointly modeling future visual dynamics and robot actions. However, existing WAMs are trained predominantly on successful trajectories, making them prone to failure when real-world execution diverges from the learned dynamics. Thi...
Lin Li, Long Chen, Kwunhang Wong et al.· 0 citations
Interactive dashboards require users to reveal and connect evidence across stateful interactions. Although graphical user interface (GUI) agents could automate this process, existing dashboard benchmarks primarily report final answers or task success. They provide limited insight into whether failures arise from mainta...
Chu-Han Zhang, Qinghongbing Xie, Zi-Yue Wang et al.· 0 citations
World Action Models (WAMs) aim to control robots by stochastically generating visual futures and then decoding actions, but empirical observations indicate that the results can strongly depend on which future is selected. We propose World-Coherent-Decoding (WCD), a self-verifying test-time planning framework that treat...
Chuhan Zhang, Seiji Ito, Kenta Hoshino et al.· 0 citations
NeuroBreak is presented, a visual analytics system that helps experts progressively unpack jailbreak mechanisms from layer-level semantics down to neuron-level behaviors and provides actionable insights for strengthening LLM defenses.
Chuhan Zhang, Ye Zhang, Bowen Shi et al.· arXiv.org· 3 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
