8 papers
Just Noticeable Difference Modeling for Token Compression in Vision-Language-Action Models
Zhuoyuan Li, Rui Zhao, Jin Wang +5
Token compression has become a key technique for reducing the inference cost of large foundation models, with approaches such as token pruning and KV-cache reuse widely adopted in…
Current Injection Spiking Neural Network for Infrared and Visible Image Fusion
Rui Zhao, Zhuoyuan Li, Wenrui Li +4
Infrared and visible image fusion (IVIF) integrates the complementary information of two modalities into a single image with richer scene content. While existing methods are largel…
Just Noticeable Difference Modeling for Deep Visual Features
Rui Zhao, Wenrui Li, Lin Zhu +2
Deep visual features are increasingly used as the interface in vision systems, motivating the need to describe feature characteristics and control feature quality for machine perce…
RLPO: Residual Listwise Preference Optimization for Long-Context Review Ranking
Hao Jiang, Zhi Yang, Annan Wang +2
Review ranking is pivotal in e-commerce for prioritizing diagnostic and authentic feedback from the deluge of user-generated content. While large language models have improved sema…
Cross-architecture universal feature coding via distribution alignment
Changsheng Gao, Shan Liu, Feng Wu +1
Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are a…
DT-UFC: Universal Large Model Feature Coding via Peaky-to-Balanced Distribution Transformation
Changsheng Gao, Zijie Liu, Li Li +3
Like image coding in visual data transmission, feature coding is essential for the distributed deployment of large models by significantly reducing transmission and storage burden.…
Compressed Feature Quality Assessment: Dataset and Baselines
Changsheng Gao, Wei Zhou, Guosheng Lin +1
The widespread deployment of large models in resource-constrained environments has underscored the need for efficient transmission of intermediate feature representations. In this…
Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark
Changsheng Gao, Yifan Ma, Qiaoxi Chen +3
Large models have achieved remarkable performance across various tasks, yet they incur significant computational costs and privacy concerns during both training and inference. Dist…