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…
Zhaoyang Li, Yanjun Li, Wangkai Li, Yujia Chen, Tianzhu Zhang
Vision-Language Models (VLMs) are costly at inference time because they must process long sequences of visual tokens. Existing token pruning methods often degrade under high compression by blindly discarding information, breaking spatial structure or collapsing diversity. We prop…
Zhaoyang Li, Ruijie Zhang, Jiaqi Liu, Zhaoji Sun
General-purpose large language models (LLMs) have demonstrated strong abilities in opendomain question answering, information extraction, and text generation. Agricultural applications, however, are domain-specific, region-dependent, time-sensitive, and safety-critical. Without d…
Xin Zhao, Zeyi Zhao, Fengnian Zhao, Jiangfan Liu, Zhaoyang Li, Xingpeng Wang, et al.
Accurate nitrogen fertilizer management determines the yield and quality of fruit trees, but there is a lack of multispectral UAV-based nitrogen fertilizer monitoring technology for orchards. Therefore, in this study, a field experiment was conducted by UAV to acquire multispectr…