Abstract: This work studies black-box adversarial attacks against deep neural networks, where the attacker only has access to the query feedback from the target model. The current state-of-the-art ...
Abstract: Differential line arrays (DLAs) hold significant potential for practical signal enhancement, but DLAs are not capable of realizing the Nth-order fully steerable function. To overcome this ...
VQ-VLA is an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more data than previous approaches. It ...
The JPEG Compression Simulator demonstrates how JPEG image compression works at a fundamental level. It provides a complete implementation of the JPEG compression pipeline with interactive ...