4 accepted papers
Protein design is a fundamental challenge in biotechnology, aiming to design novel sequences with specific functions within the vast space of possible proteins. Recent advances in deep generative models have enabled function-based protein design from textual descriptions, yet struggle with structura…
We introduce a new dynamic vocabulary for language models. It can involve arbitrary text spans during generation. These text spans act as basic generation bricks, akin to tokens in the traditional static vocabularies. We show that, the ability to generate multi-tokens atomically improve both generat…
"Shadow removal is an important topic in image restoration, and it can benefit many computer vision tasks. State-of-the-art shadow-removal methods typically employ deep learning by minimizing a pixel-level difference between the de-shadowed region and their corresponding (pseudo) shadow-free version…
Untethered microrobot has been regarded as one of the most powerful tools for performing specific in vitro/vivo tasks, especially magnetic actuated microrobot owing to its biocompatible energy source. However, although numerous design and fabrication technologies of magnetic microrobot have been dev