The results revealed that ChatGPT-4's internal consistency was moderate and was markedly improved by detailed prompts on content-related dimensions, but showed minimal gains on linguistic dimensions (LR/GRA).
Boyu Wang, Yun-Jian Zhang· Language Education & Ass...· 0 citations
FMM-WM (Factual--Interventional Recurrent World Model), a compact pixel world model designed around a typed, goal--comparable configuration from a 128-dimensional dynamic fiber used for prediction but excluded from the terminal goal cost, is introduced.
Yi-Lun Wu, Yun-Jian Zhang, Ao Li et al.· 0 citations
HyperWorld, a controlled study of state serialization for learned textual world models, shows that higher-order state organization is a simple but effective inductive bias for learned symbolic world models, especially when model capacity is limited or test environments differ from training.
Yun-Jian Zhang, Chen-Wei Liang, Tian-Yi Zhang 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.