Latent world models learn to predict observed transitions, yet low prediction error alone does not guarantee reliable planning. Inspired by self tickling experiments in neuroscience showing that disrupting motor sensory correspondence increases prediction mismatch, we examine whether learned world models preserve an an...
Jin-Ping Wang, Zhi-Qiang Gao, Xian-Tong Zhen et al.· 0 citations
Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected evidence rather than the ability to seek it across clinical records and longitudinal imaging. We propose CASE: a series of role-specific Clinical Agents for Seeking Evide...
Min-Ye Shao, Chao-Hui Yu, Yi-Xuan Wu et al.· 0 citations
This work decomposes multi-step rollout error into the errors introduced at individual steps and their propagation through subsequent transitions, showing that state-affine dynamics are precisely the differentiable transitions with state-independent Jacobians, eliminating the nonlinear propagation residual and making t...
Bo-Yuan Zhang, Ying-Jun Du, Xian-Tong Zhen et al.· 0 citations
This work model step-by-step reasoning as a finite-horizon decision process and introduce Monte Carlo value evaluation on the reasoning tree to provide intermediate supervision signals and effectively enhances the performance of benchmark MLLMs in visual-based spatial understanding and reasoning tasks.
Ling Lin, Yang Bai, Cong-Cong Zhu et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
