8 papers
FairJudge: An Adaptive, Debiased, and Consistent LLM-as-a-Judge
Bo Yang, Lanfei Feng, Yunkui Chen +3
Existing LLM-as-a-Judge systems suffer from three fundamental limitations: limited adaptivity to task- and domain-specific evaluation criteria, systematic biases driven by non-sema…
GeoVista: Visually Grounded Active Perception for Vision-Language Understanding of Ultra-High-Resolution Remote Sensing Images
Jiashun Zhu, Ronghao Fu, Jiasen Hu +3
Interpreting ultra-high-resolution (UHR) remote sensing images requires models to search for sparse and tiny visual evidence across large-scale scenes. Existing remote sensing visi…
From Web to Pixels: Bringing Agentic Search into Visual Perception
Bokang Yang, Xinyi Sun, Kaituo Feng +3
Visual perception connects high-level semantic understanding to pixel-level perception, but most existing settings assume that the decisive evidence for identifying a target is alr…
ZPD Detector: Data Selection via Capability-Difficulty Alignment for Large Language Models
Bo Yang, Yunkui Chen, Lanfei Feng +2
As the cost of training large language models continues to increase and high-quality training data become increasingly scarce, selecting high-value samples or synthesizing effectiv…
AgriAgent: Contract-Driven Planning and Capability-Aware Tool Orchestration in Real-World Agriculture
Bo Yang, Yu Zhang, Yunkui Chen +4
Intelligent agent systems in real-world agricultural scenarios must handle diverse tasks under multimodal inputs, ranging from lightweight information understanding to complex mult…
AgriGPT-Omni: A Unified Speech-Vision-Text Framework for Multilingual Agricultural Intelligence
Bo Yang, Lanfei Feng, Yunkui Chen +5
Despite rapid advances in multimodal large language models, agricultural applications remain constrained by the lack of multilingual speech data, unified multimodal architectures,…