Abstract: With advances in CLIP-based models for long-text processing, the insufficient ability to capture visual details has emerged as a key bottleneck for fine-grained image–text matching. Our ...

Abstract: A microplastic detection method employing two dual-mode complementary split-ring resonators (CSRRs), operating separately at the 2.45- and 5.8-GHz ISM bands, is proposed for measuring the ...

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.