Penguin-VL is a compact vision-language model family built to study how far multimodal efficiency can be pushed by redesigning the vision encoder, rather than only scaling data or model size.

Abstract: This article presents a 7-bit, 1.15-GS/s, 2.6-bit/cycle asynchronous successive approximation register (SAR) analog-to-digital converter (ADC) that incorporates a comparator decision skip ...

Abstract: End-to-end autonomous driving has emerged as a promising paradigm integrating perception, decision-making, and control within a unified learning framework. Recently, Vision-Language Models ...