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: The promotion of the HEVC standard has significantly alleviated the burden of network transmission and video storage. However, its inherent complexity and data dependencies pose a ...

Abstract: To ensure the flexibility of Earth Observation satellite missions, it is essential to have highly adaptable communication systems equipped with efficient modulation and coding schemes. The ...

This is the official repository with PyTorch implementation of LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection. ☀️ If you find this work useful for your research, please kindly star ...