4 papers indexed
Zenghuang Fu, Zhaoyang Li, Qiuyuan Ai, Haoyu Wu, Minghui Wu, Chenxu Zhao, et al.
Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly shape future practice. External skill memories preserve procedural experience but are typically lea…
Mingjia Shi, Shuo Wang, Xiaobo Wang, Sifan Zhou, Kai Wang, Tianyu Fu, et al.
Vision-language alignment, the stage that bridges pretrained vision encoders and large language models, is widely treated as a form of pretraining requiring full-parameter updates. We challenge this view and investigate what happens when low-rank adaptation is applied to the LLM…
Wei Dong, Tianyu Fu, Zhe Yu, Hanning Wang, Anyang Su, Zhizhou Fang, et al.
As web agents increasingly demonstrate capabilities in automated task execution, the development of robust evaluation frameworks for assessing their navigation and task completion performance has emerged as a critical research priority. However, existing benchmarks exhibit fundam…
Bole Liu, Li Qiao, Minghui Wu, Yulin Shao, Zhen Gao
In the Internet of Vehicles (IoV), transmitting high-dimensional multi-modal sensory data to edge servers for time-sensitive tasks faces severe spectrum bottlenecks. To address this, we propose a foundation model-driven over-the-air token fusion (AirTF) framework for task-oriente…