Zobrazeno 1 - 10
of 150
pro vyhledávání: '"Koyejo, Sanmi"'
Autor:
Niknazar, Mohammad, Haley, Paul V, Ramanan, Latha, Truong, Sang T., Shrinivasan, Yedendra, Bhowmick, Ayan Kumar, Dey, Prasenjit, Jagmohan, Ashish, Maheshwari, Hema, Ponoth, Shom, Smith, Robert, Vempaty, Aditya, Haber, Nick, Koyejo, Sanmi, Sundararajan, Sharad
Generative AI holds the promise of enabling a range of sought-after capabilities and revolutionizing workflows in various consumer and enterprise verticals. However, putting a model in production involves much more than just generating an output. It
Externí odkaz:
http://arxiv.org/abs/2408.01452
Autor:
Schaeffer, Rylan, Valentine, Dan, Bailey, Luke, Chua, James, Eyzaguirre, Cristóbal, Durante, Zane, Benton, Joe, Miranda, Brando, Sleight, Henry, Hughes, John, Agrawal, Rajashree, Sharma, Mrinank, Emmons, Scott, Koyejo, Sanmi, Perez, Ethan
The integration of new modalities into frontier AI systems offers exciting capabilities, but also increases the possibility such systems can be adversarially manipulated in undesirable ways. In this work, we focus on a popular class of vision-languag
Externí odkaz:
http://arxiv.org/abs/2407.15211
Autor:
Reuel, Anka, Bucknall, Ben, Casper, Stephen, Fist, Tim, Soder, Lisa, Aarne, Onni, Hammond, Lewis, Ibrahim, Lujain, Chan, Alan, Wills, Peter, Anderljung, Markus, Garfinkel, Ben, Heim, Lennart, Trask, Andrew, Mukobi, Gabriel, Schaeffer, Rylan, Baker, Mauricio, Hooker, Sara, Solaiman, Irene, Luccioni, Alexandra Sasha, Rajkumar, Nitarshan, Moës, Nicolas, Ladish, Jeffrey, Guha, Neel, Newman, Jessica, Bengio, Yoshua, South, Tobin, Pentland, Alex, Koyejo, Sanmi, Kochenderfer, Mykel J., Trager, Robert
AI progress is creating a growing range of risks and opportunities, but it is often unclear how they should be navigated. In many cases, the barriers and uncertainties faced are at least partly technical. Technical AI governance, referring to technic
Externí odkaz:
http://arxiv.org/abs/2407.14981
Autor:
Sun, Yu, Li, Xinhao, Dalal, Karan, Xu, Jiarui, Vikram, Arjun, Zhang, Genghan, Dubois, Yann, Chen, Xinlei, Wang, Xiaolong, Koyejo, Sanmi, Hashimoto, Tatsunori, Guestrin, Carlos
Self-attention performs well in long context but has quadratic complexity. Existing RNN layers have linear complexity, but their performance in long context is limited by the expressive power of their hidden state. We propose a new class of sequence
Externí odkaz:
http://arxiv.org/abs/2407.04620
Autor:
Panda, Ashwinee, Isik, Berivan, Qi, Xiangyu, Koyejo, Sanmi, Weissman, Tsachy, Mittal, Prateek
Existing methods for adapting large language models (LLMs) to new tasks are not suited to multi-task adaptation because they modify all the model weights -- causing destructive interference between tasks. The resulting effects, such as catastrophic f
Externí odkaz:
http://arxiv.org/abs/2406.16797
In-context learning is a powerful capability of certain machine learning models that arguably underpins the success of today's frontier AI models. However, in-context learning is critically limited to settings where the in-context distribution of int
Externí odkaz:
http://arxiv.org/abs/2406.12785
Autor:
Madaan, Lovish, Singh, Aaditya K., Schaeffer, Rylan, Poulton, Andrew, Koyejo, Sanmi, Stenetorp, Pontus, Narang, Sharan, Hupkes, Dieuwke
Evaluation benchmarks are the cornerstone of measuring capabilities of large language models (LLMs), as well as driving progress in said capabilities. Originally designed to make claims about capabilities (or lack thereof) in fully pretrained models,
Externí odkaz:
http://arxiv.org/abs/2406.10229
Last-layer retraining methods have emerged as an efficient framework for correcting existing base models. Within this framework, several methods have been proposed to deal with correcting models for subgroup fairness with and without group membership
Externí odkaz:
http://arxiv.org/abs/2406.09561
Autor:
Schaeffer, Rylan, Lecomte, Victor, Pai, Dhruv Bhandarkar, Carranza, Andres, Isik, Berivan, Unell, Alyssa, Khona, Mikail, Yerxa, Thomas, LeCun, Yann, Chung, SueYeon, Gromov, Andrey, Shwartz-Ziv, Ravid, Koyejo, Sanmi
Maximum Manifold Capacity Representations (MMCR) is a recent multi-view self-supervised learning (MVSSL) method that matches or surpasses other leading MVSSL methods. MMCR is intriguing because it does not fit neatly into any of the commonplace MVSSL
Externí odkaz:
http://arxiv.org/abs/2406.09366
Autor:
Schaeffer, Rylan, Schoelkopf, Hailey, Miranda, Brando, Mukobi, Gabriel, Madan, Varun, Ibrahim, Adam, Bradley, Herbie, Biderman, Stella, Koyejo, Sanmi
Predictable behavior from scaling advanced AI systems is an extremely desirable property. Although a well-established literature exists on how pretraining performance scales, the literature on how particular downstream capabilities scale is significa
Externí odkaz:
http://arxiv.org/abs/2406.04391