Zobrazeno 1 - 10
of 301
pro vyhledávání: '"Lu, Alex"'
Growing research in sign language recognition, generation, and translation AI has been accompanied by calls for ethical development of such technologies. While these works are crucial to helping individual researchers do better, there is a notable la
Externí odkaz:
http://arxiv.org/abs/2403.02563
Autor:
Desai, Aashaka, Berger, Lauren, Minakov, Fyodor O., Milan, Vanessa, Singh, Chinmay, Pumphrey, Kriston, Ladner, Richard E., Daumé III, Hal, Lu, Alex X., Caselli, Naomi, Bragg, Danielle
Sign languages are used as a primary language by approximately 70 million D/deaf people world-wide. However, most communication technologies operate in spoken and written languages, creating inequities in access. To help tackle this problem, we relea
Externí odkaz:
http://arxiv.org/abs/2304.05934
Histopathology is critical for the diagnosis of many diseases, including cancer. These protocols typically require pathologists to manually evaluate slides under a microscope, which is time-consuming and subjective, leading to interest in machine lea
Externí odkaz:
http://arxiv.org/abs/2303.02241
Autor:
Wu, Kevin E., Yang, Kevin K., Berg, Rianne van den, Zou, James Y., Lu, Alex X., Amini, Ava P.
The ability to computationally generate novel yet physically foldable protein structures could lead to new biological discoveries and new treatments targeting yet incurable diseases. Despite recent advances in protein structure prediction, directly g
Externí odkaz:
http://arxiv.org/abs/2209.15611
Motivation: In recent years, image-based biological assays have steadily become high-throughput, sparking a need for fast automated methods to extract biologically-meaningful information from hundreds of thousands of images. Taking inspiration from t
Externí odkaz:
http://arxiv.org/abs/2111.11646
Large self-supervised models pretrained on millions of protein sequences have recently gained popularity in generating embeddings of protein sequences for protein function prediction. However, the absence of random baselines makes it difficult to con
Externí odkaz:
http://arxiv.org/abs/2104.14661
Classic asset management approaches begin by inventorying all infrastructure assets and then assigning maintenance tasks and resources. Our approach collects similar data, but by starting with current personnel assignment and describing their job res
Externí odkaz:
http://arxiv.org/abs/2103.02025
Electric railways are fast, clean, and safe, but complex to operate and maintain. Electric traction infrastructure includes signal power and feeder lines that remain live during isolations and complicate maintenance processes. Stakeholders involved i
Externí odkaz:
http://arxiv.org/abs/2102.04517
Self-supervised representation learning of biological sequence embeddings alleviates computational resource constraints on downstream tasks while circumventing expensive experimental label acquisition. However, existing methods mostly borrow directly
Externí odkaz:
http://arxiv.org/abs/2012.13475
Autor:
Yang, Karren, Goldman, Samuel, Jin, Wengong, Lu, Alex, Barzilay, Regina, Jaakkola, Tommi, Uhler, Caroline
In this paper, we aim to synthesize cell microscopy images under different molecular interventions, motivated by practical applications to drug development. Building on the recent success of graph neural networks for learning molecular embeddings and
Externí odkaz:
http://arxiv.org/abs/2006.08532