Zobrazeno 1 - 10
of 1 097
pro vyhledávání: '"Roberts, Nicholas A."'
Autor:
Tan, Wenxuan, Roberts, Nicholas, Huang, Tzu-Heng, Zhao, Jitian, Cooper, John, Guo, Samuel, Duan, Chengyu, Sala, Frederic
Parameter-efficient fine-tuning (PEFT) techniques have unlocked the potential to cheaply and easily specialize large pretrained models. However, the most prominent approaches, like low-rank adapters (LoRA), depend on heuristics or rules-of-thumb for
Externí odkaz:
http://arxiv.org/abs/2408.17383
Autor:
Roberts, Nicholas, Guo, Samuel, Gao, Zhiqi, GNVV, Satya Sai Srinath Namburi, Cromp, Sonia, Wu, Chengjun, Duan, Chengyu, Sala, Frederic
While Transformers underpin modern large language models (LMs), there is a growing list of alternative architectures with new capabilities, promises, and tradeoffs. This makes choosing the right LM architecture challenging. Recently-proposed $\textit
Externí odkaz:
http://arxiv.org/abs/2406.00894
Autor:
Chen, Mayee F., Roberts, Nicholas, Bhatia, Kush, Wang, Jue, Zhang, Ce, Sala, Frederic, Ré, Christopher
The quality of training data impacts the performance of pre-trained large language models (LMs). Given a fixed budget of tokens, we study how to best select data that leads to good downstream model performance across tasks. We develop a new framework
Externí odkaz:
http://arxiv.org/abs/2307.14430
Autor:
Roberts, Nicholas, Li, Xintong, Adila, Dyah, Cromp, Sonia, Huang, Tzu-Heng, Zhao, Jitian, Sala, Frederic
Machine learning models -- including prominent zero-shot models -- are often trained on datasets whose labels are only a small proportion of a larger label space. Such spaces are commonly equipped with a metric that relates the labels via distances b
Externí odkaz:
http://arxiv.org/abs/2307.12226
Autor:
Roberts, Nicholas, Kim, Inchan
Publikováno v:
Internet Research, 2023, Vol. 34, Issue 4, pp. 1165-1197.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/INTR-01-2022-0077
Autor:
Boudreau, Mariah C., Allen, Andrea J., Roberts, Nicholas J., Allard, Antoine, Hébert-Dufresne, Laurent
Publikováno v:
Bull. of Math. Biol. 85(2023)118
Forecasting disease spread is a critical tool to help public health officials design and plan public health interventions.However, the expected future state of an epidemic is not necessarily well defined as disease spread is inherently stochastic, co
Externí odkaz:
http://arxiv.org/abs/2302.03210
Autor:
Chen, Adela, Roberts, Nicholas
Publikováno v:
Information Technology & People, 2023, Vol. 37, Issue 3, pp. 1103-1125.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/ITP-07-2022-0562
Weak supervision (WS) is a rich set of techniques that produce pseudolabels by aggregating easily obtained but potentially noisy label estimates from a variety of sources. WS is theoretically well understood for binary classification, where simple ap
Externí odkaz:
http://arxiv.org/abs/2211.13375
Autor:
Tu, Renbo, Roberts, Nicholas, Prasad, Vishak, Nayak, Sibasis, Jain, Paarth, Sala, Frederic, Ramakrishnan, Ganesh, Talwalkar, Ameet, Neiswanger, Willie, White, Colin
The challenge that climate change poses to humanity has spurred a rapidly developing field of artificial intelligence research focused on climate change applications. The climate change AI (CCAI) community works on a diverse, challenging set of probl
Externí odkaz:
http://arxiv.org/abs/2210.03324
Autor:
Roberts, Nicholas, Li, Xintong, Huang, Tzu-Heng, Adila, Dyah, Schoenberg, Spencer, Liu, Cheng-Yu, Pick, Lauren, Ma, Haotian, Albarghouthi, Aws, Sala, Frederic
Weak supervision (WS) is a powerful method to build labeled datasets for training supervised models in the face of little-to-no labeled data. It replaces hand-labeling data with aggregating multiple noisy-but-cheap label estimates expressed by labeli
Externí odkaz:
http://arxiv.org/abs/2208.14362