World models predict action-conditioned futures and serve as critical internal simulators for downstream planning and control. However, catastrophic prediction failures of world models could dangerously propagate through the control pipeline, as subsequent agent or model training and decision-making depend heavily on t...
Zhanpeng Shi, Zi Liang, Rong Feng et al.· 0 citations
Control Memory Interference is introduced, a controlled diagnostic and data-generation framework for studying how agent memory evolves under different memory relationships and shows that memory evolution is shaped not only by memory scale, but also by interactions among accumulated experiences.
Ao Ding, Hong-Zong Li, Shi-Qin Tang et al.· 1 citation
Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at low token cost. However, its increased complexity may introduce new security vulnerabilities. In this paper, we present, to the best of our knowledge, the first pure black...
Wenbo Sun, Hong-Zong Li, Yanyun Wang et al.· 0 citations
The Emergent Modular Atomic Network (EMAN), an optimization-driven framework for exposing an antisymmetric growth direction through latent relative phases without instantiating a second path, and for monitoring multiple decision signals during training to transform local optimization evidence into a structural decision...
Chen Fang, Jingchen Li, Hong-Zong Li 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.
