BioNeMo Framework: a modular, high-performance library for AI model development in drug discovery

Autor: John, Peter St., Lin, Dejun, Binder, Polina, Greaves, Malcolm, Shah, Vega, John, John St., Lange, Adrian, Hsu, Patrick, Illango, Rajesh, Ramanathan, Arvind, Anandkumar, Anima, Brookes, David H, Busia, Akosua, Mahajan, Abhishaike, Malina, Stephen, Prasad, Neha, Sinai, Sam, Edwards, Lindsay, Gaudelet, Thomas, Regep, Cristian, Steinegger, Martin, Rost, Burkhard, Brace, Alexander, Hippe, Kyle, Naef, Luca, Kamata, Keisuke, Armstrong, George, Boyd, Kevin, Cao, Zhonglin, Chou, Han-Yi, Chu, Simon, Costa, Allan dos Santos, Darabi, Sajad, Dawson, Eric, Didi, Kieran, Fu, Cong, Geiger, Mario, Gill, Michelle, Hsu, Darren, Kaushik, Gagan, Korshunova, Maria, Kothen-Hill, Steven, Lee, Youhan, Liu, Meng, Livne, Micha, McClure, Zachary, Mitchell, Jonathan, Moradzadeh, Alireza, Mosafi, Ohad, Nashed, Youssef, Paliwal, Saee, Peng, Yuxing, Rabhi, Sara, Ramezanghorbani, Farhad, Reidenbach, Danny, Ricketts, Camir, Roland, Brian, Shah, Kushal, Shimko, Tyler, Sirelkhatim, Hassan, Srinivasan, Savitha, Stern, Abraham C, Toczydlowska, Dorota, Veccham, Srimukh Prasad, Venanzi, Niccolò Alberto Elia, Vorontsov, Anton, Wilber, Jared, Wilkinson, Isabel, Wong, Wei Jing, Xue, Eva, Ye, Cory, Yu, Xin, Zhang, Yang, Zhou, Guoqing, Zandstein, Becca, Dallago, Christian, Trentini, Bruno, Kucukbenli, Emine, Rvachov, Timur, Calleja, Eddie, Israeli, Johnny, Clifford, Harry, Haukioja, Risto, Haemel, Nicholas, Tretina, Kyle, Tadimeti, Neha, Costa, Anthony B

Artificial Intelligence models encoding biology and chemistry are opening new routes to high-throughput and high-quality in-silico drug development. However, their training increasingly relies on computational scale, with recent protein language mode

Externí odkaz: http://arxiv.org/abs/2411.10548

PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning

Autor: Ma'sum, Muhammad Anwar, Pratama, Mahardhika, Ramasamy, Savitha, Liu, Lin, Habibullah, Habibullah, Kowalczyk, Ryszard

Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Existing FCIL methods call for high communication costs and exemplars from

Externí odkaz: http://arxiv.org/abs/2407.20705

Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification

Autor: Ma'sum, Muhammad Anwar, Pratama, Mahardhika, Savitha, Ramasamy, Liu, Lin, Habibullah, Kowalczyk, Ryszard

A continual learning (CL) model is desired for remote sensing image analysis because of varying camera parameters, spectral ranges, resolutions, etc. There exist some recent initiatives to develop CL techniques in this domain but they still depend on

Externí odkaz: http://arxiv.org/abs/2406.18574

Cross-Domain Continual Learning via CLAMP

Autor: Weng, Weiwei, Pratama, Mahardhika, Zhang, Jie, Chen, Chen, Yee, Edward Yapp Kien, Savitha, Ramasamy

Artificial neural networks, celebrated for their human-like cognitive learning abilities, often encounter the well-known catastrophic forgetting (CF) problem, where the neural networks lose the proficiency in previously acquired knowledge. Despite nu

Externí odkaz: http://arxiv.org/abs/2405.07142

Initial Decoding with Minimally Augmented Language Model for Improved Lattice Rescoring in Low Resource ASR

Autor: Murthy, Savitha, Sitaram, Dinkar

This paper addresses the problem of improving speech recognition accuracy with lattice rescoring in low-resource languages where the baseline language model is insufficient for generating inclusive lattices. We minimally augment the baseline language

Externí odkaz: http://arxiv.org/abs/2403.10937