3 papers
cs.CL2026
ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
Jitai Hao, Qiang Huang, Yaowei Wang +2
Efficient long-context inference faces two coupled bottlenecks: KV-cache memory grows linearly with context length, while attention computation grows quadratically. Existing approa…
cs.CV2025
Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
Xiaoxing You, Qiang Huang, Lingyu Li +4
News image captioning aims to produce journalistically informative descriptions by combining visual content with contextual cues from associated articles. Despite recent advances,…
cs.IR2024
Holistic Utility Preference Learning for Listwise Alignment
Jiacong Zhou, Xianyun Wang, Min Zhang +1
Aligning large language models with human preferences is essential for improving interaction quality and safety by ensuring outputs better reflect human values. A promising strateg…