2 citations · 2 across the 10 of their papers we have counts for
5 papers · 1 filter
When Links Mislead: Label-Free Structural Polarity for Zero-Shot Classification of Web Pages
Hanshuai Cui, Zhiqing Tang, Zhi Yao +2
Web platforms such as digital libraries, online stores and university sites must classify new pages before anyone labels them. Large language models (LLMs) can label each page from…
RetryRoute: Retry-Aware Model Routing for Agentic Image Editing Services
Hanshuai Cui, Zhiqing Tang, Zhi Yao +2
Web agents increasingly edit images by calling open editing models in a critique-and-retry loop, and these models differ in cost by more than an order of magnitude. After every rej…
NormDetect: Anchored Calibration for Low-False-Positive Detection of Machine-Generated Web Text
Hanshuai Cui, Fanshuai Meng, Zhiqing Tang
Web platforms screen posts for text written by large language models, and every false flag hits a human writer. Detectors must therefore run at a very low false positive rate (FPR)…
Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
Qianli Ma, Zhiqing Tang, Fanshuai Meng +3
Small language models deployed under cost, latency, or privacy constraints cannot simply switch to larger models when reasoning fails. Multi-candidate generate-then-rerank offers a…
Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching
Qianli Ma, Zhiqing Tang, Hanshuai Cui +2
Disaggregated serving alleviates memory bottlenecks in Large Language Model (LLM) inference but creates a severe communication bottleneck: transmitting high-dimensional Key-Value (…