Memory-augmented agents maintain compact user profiles throughout extended conversations, enabling personalized and consistent responses without the need to process the entire dialogue history. The quality of these user profiles relies on the underlying memory management strategy: at each step, the agent must determine...
Yu-Peng Han, Shuo-Chen Liu, Kai Zhang et al.· 2 citations
Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessing raw clips for every query becomes computationally prohibitive. Memory systems offer a scalable alternative by compacting videos into text...
Guang-Zhi Xiong, Xin-Yuan Zhang, Xiao Yang et al.· 0 citations
This paper proposes Distributional Orthogonalization Loss (DO-loss), an auxiliary regularization that shifts the focus from static weight diversity to dynamic routing behavior, and introduces the Replica Expert Mechanism (REM), which improves load balancing through a two-tiered strategy.
Jin-Fan He, Yun-Zhuo Liu, Kai Zhang et al.· 0 citations
This work proposes Adaptive Evidential Multimodal Representation Learning (AEMRL), a framework aligned with this multi-level view of uncertainty that consistently enhances task accuracy, reduces calibration error, and improves robustness to noise, semantic conflict, and missing modalities.
Yu-Peng Han, Kai Zhang, Xian-Quan Wang et al.· Proceedings of the Thirty-Fi...· 0 citations
Meta-Task is proposed, a framework that redefines terminal task synthesis as a Terminal-Bench-format task itself: an agent operates within a real container environment to iteratively generate, execute, and verify tasks, so that synthesized components are checked for internal consistency and executability within the gen...
Zhi-Hong Pan, Ji-Yuan He, Kai Zhang et al.· arXiv.org· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
