Showing cs.LGShow all
2 papers · 1 filter
cs.LG2025
MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
Kunxi Li, Zhonghua Jiang, Zhouzhou Shen +5
This paper introduces MadaKV, a modality-adaptive key-value (KV) cache eviction strategy designed to enhance the efficiency of multimodal large language models (MLLMs) in long-cont…
cs.LG2024
MergeNet: Knowledge Migration across Heterogeneous Models, Tasks, and Modalities
Kunxi Li, Tianyu Zhan, Kairui Fu +6
In this study, we focus on heterogeneous knowledge transfer across entirely different model architectures, tasks, and modalities. Existing knowledge transfer methods (e.g., backbon…