5 papers
Relevant but Incomplete: Referential Dangling as a Paradigm-Level Failure Mode in Hard Prompt Compression
Zhengpei Hu, Kai Li, Dapeng Fu +5
Hard prompt compression reduces long-context inference cost by independently scoring tokens, sentences, or chunks and retaining the highest-scoring units under a budget. We identif…
BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection
Zhengpei Hu, Kai Li, Dapeng Fu +4
The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference latency and informatio…
EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis
Jiayan Chen, Kai Li, Yulu Zhao +2
Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have bee…
BERP: A Blind Estimator of Room Parameters for Single-Channel Noisy Speech Signals
Lijun Wang, Yixian Lu, Ziyan Gao +4
Room acoustical parameters (RAPs), room geometrical parameters (RGPs) and instantaneous occupancy level are essential metrics for parameterizing the room acoustical characteristics…
HES-UNet: A U-Net for Hepatic Echinococcosis Lesion Segmentation
Jiayan Chen, Kai Li, Zhanjin Wang +2
Hepatic echinococcosis (HE) is a prevalent disease in economically underdeveloped pastoral areas, where adequate medical resources are usually lacking. Existing methods often ignor…