Generative recommendation can reproduce a wider beam's ranked output with roughly half the prefix-capacity budget by reallocating retention capacity across semantic-ID positions. We identify a \emph{first-step coverage bottleneck}: across six full-test settings of the TIGER generative recommender spanning three domains...
Current image-to-video models achieve visual realism and physical plausibility, but reasoning about mental states remains unexplored. Actions are driven by belief, desire, and perception, requiring inference beyond explicit instructions. We introduce MindWorldBench to evaluate mental-state-conditioned video generation....
Rui-Qi Li, Xuan-Yi Liu, Si-Jia Li et al.· 0 citations
Action-JND is introduced, which extends JND modeling to embodied perception by defining noticeability through the language-conditioned action response of a vision-language-action (VLA) policy in closed-loop control, and develops a lightweight token-wise JND estimator in deep visual-feature space to predict the maximum...
Zhuo-Yuan Li, Rui Zhao, Jin Wang 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.