2 papers
cs.CV2024
OmniVLM: A Token-Compressed, Sub-Billion-Parameter Vision-Language Model for Efficient On-Device Inference
Wei Chen, Zhiyuan Li, Shuo Xin
We present OmniVLM, a sub-billion-parameter vision-language model for efficient on-device inference. OmniVLM introduces a token compression mechanism that reduces visual token sequ…
cs.CL2024
Squid: Long Context as a New Modality for Energy-Efficient On-Device Language Models
Wei Chen, Zhiyuan Li, Shuo Xin +1
This paper presents Dolphin, a novel decoder-decoder architecture for energy-efficient processing of long contexts in language models. Our approach addresses the significant energy…