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: 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 ...

Abstract: Combining a global tracking system with a local measurement system constitutes an efficient approach for meter-scale component measurement. The transformation matrix between the local system ...

Key Challenge: There is a tension between "cross-dataset transferability" and "capturing inter-channel dependencies." Fixed-channel encoders are expressive but tied to specific channels; per-channel ...

The latest VisionOS updates give Apple's headset a few things that future glasses could also add. There are other interesting additions, too. I started with CNET reviewing laptops in 2009. Now I ...