Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Petryk, Suzanne"'
Autor:
Gupta, Ritwik, Walker, Leah, Corona, Rodolfo, Fu, Stephanie, Petryk, Suzanne, Napolitano, Janet, Darrell, Trevor, Reddie, Andrew W.
Current regulations on powerful AI capabilities are narrowly focused on "foundation" or "frontier" models. However, these terms are vague and inconsistently defined, leading to an unstable foundation for governance efforts. Critically, policy debates
Externí odkaz:
http://arxiv.org/abs/2409.17216
Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image segmentation and active learning. However, their application in modern
Externí odkaz:
http://arxiv.org/abs/2408.05097
Autor:
Bordes, Florian, Pang, Richard Yuanzhe, Ajay, Anurag, Li, Alexander C., Bardes, Adrien, Petryk, Suzanne, Mañas, Oscar, Lin, Zhiqiu, Mahmoud, Anas, Jayaraman, Bargav, Ibrahim, Mark, Hall, Melissa, Xiong, Yunyang, Lebensold, Jonathan, Ross, Candace, Jayakumar, Srihari, Guo, Chuan, Bouchacourt, Diane, Al-Tahan, Haider, Padthe, Karthik, Sharma, Vasu, Xu, Hu, Tan, Xiaoqing Ellen, Richards, Megan, Lavoie, Samuel, Astolfi, Pietro, Hemmat, Reyhane Askari, Chen, Jun, Tirumala, Kushal, Assouel, Rim, Moayeri, Mazda, Talattof, Arjang, Chaudhuri, Kamalika, Liu, Zechun, Chen, Xilun, Garrido, Quentin, Ullrich, Karen, Agrawal, Aishwarya, Saenko, Kate, Celikyilmaz, Asli, Chandra, Vikas
Following the recent popularity of Large Language Models (LLMs), several attempts have been made to extend them to the visual domain. From having a visual assistant that could guide us through unfamiliar environments to generative models that produce
Externí odkaz:
http://arxiv.org/abs/2405.17247
Autor:
Petryk, Suzanne, Chan, David M., Kachinthaya, Anish, Zou, Haodi, Canny, John, Gonzalez, Joseph E., Darrell, Trevor
Despite recent advances in multimodal pre-training for visual description, state-of-the-art models still produce captions containing errors, such as hallucinating objects not present in a scene. The existing prominent metric for object hallucination,
Externí odkaz:
http://arxiv.org/abs/2404.02904
The evaluation of machine-generated image captions poses an interesting yet persistent challenge. Effective evaluation measures must consider numerous dimensions of similarity, including semantic relevance, visual structure, object interactions, capt
Externí odkaz:
http://arxiv.org/abs/2310.12971
Autor:
Petryk, Suzanne, Whitehead, Spencer, Gonzalez, Joseph E., Darrell, Trevor, Rohrbach, Anna, Rohrbach, Marcus
The ability to judge whether a caption correctly describes an image is a critical part of vision-language understanding. However, state-of-the-art models often misinterpret the correctness of fine-grained details, leading to errors in outputs such as
Externí odkaz:
http://arxiv.org/abs/2305.07021
Autor:
Miao, Kevin, Gokul, Akash, Singh, Raghav, Petryk, Suzanne, Gonzalez, Joseph, Keutzer, Kurt, Darrell, Trevor, Reed, Colorado
Recent trends in self-supervised representation learning have focused on removing inductive biases from training pipelines. However, inductive biases can be useful in settings when limited data are available or provide additional insight into the und
Externí odkaz:
http://arxiv.org/abs/2209.03745
Autor:
Whitehead, Spencer, Petryk, Suzanne, Shakib, Vedaad, Gonzalez, Joseph, Darrell, Trevor, Rohrbach, Anna, Rohrbach, Marcus
Machine learning has advanced dramatically, narrowing the accuracy gap to humans in multimodal tasks like visual question answering (VQA). However, while humans can say "I don't know" when they are uncertain (i.e., abstain from answering a question),
Externí odkaz:
http://arxiv.org/abs/2204.13631
Autor:
Petryk, Suzanne, Dunlap, Lisa, Nasseri, Keyan, Gonzalez, Joseph, Darrell, Trevor, Rohrbach, Anna
While real world challenges typically define visual categories with language words or phrases, most visual classification methods define categories with numerical indices. However, the language specification of the classes provides an especially usef
Externí odkaz:
http://arxiv.org/abs/2202.08926
Autor:
Ebrahimi, Sayna, Petryk, Suzanne, Gokul, Akash, Gan, William, Gonzalez, Joseph E., Rohrbach, Marcus, Darrell, Trevor
The goal of continual learning (CL) is to learn a sequence of tasks without suffering from the phenomenon of catastrophic forgetting. Previous work has shown that leveraging memory in the form of a replay buffer can reduce performance degradation on
Externí odkaz:
http://arxiv.org/abs/2010.01528