Zobrazeno 1 - 10
of 1 295
pro vyhledávání: '"Meyer, Gregory"'
Autor:
Ye, Mao, Meyer, Gregory P., Zhang, Zaiwei, Park, Dennis, Mustikovela, Siva Karthik, Chai, Yuning, Wolff, Eric M
Ensuring robust performance on long-tail examples is an important problem for many real-world applications of machine learning, such as autonomous driving. This work focuses on the problem of identifying rare examples within a corpus of unlabeled dat
Externí odkaz:
http://arxiv.org/abs/2409.15486
Autor:
Zhang, Zaiwei, Meyer, Gregory P., Lu, Zhichao, Shrivastava, Ashish, Ravichandran, Avinash, Wolff, Eric M.
For visual recognition, knowledge distillation typically involves transferring knowledge from a large, well-trained teacher model to a smaller student model. In this paper, we introduce an effective method to distill knowledge from an off-the-shelf v
Externí odkaz:
http://arxiv.org/abs/2408.16930
The multiplication of superpositions of numbers is a core operation in many quantum algorithms. The standard method for multiplication (both classical and quantum) has a runtime quadratic in the size of the inputs. Quantum circuits with asymptoticall
Externí odkaz:
http://arxiv.org/abs/2403.18006
Autor:
Xie, Yichen, Chen, Hongge, Meyer, Gregory P., Lee, Yong Jae, Wolff, Eric M., Tomizuka, Masayoshi, Zhan, Wei, Chai, Yuning, Huang, Xin
Due to the lack of depth cues in images, multi-frame inputs are important for the success of vision-based perception, prediction, and planning in autonomous driving. Observations from different angles enable the recovery of 3D object states from 2D i
Externí odkaz:
http://arxiv.org/abs/2402.15583
Autor:
Cai, Mu, Liu, Haotian, Park, Dennis, Mustikovela, Siva Karthik, Meyer, Gregory P., Chai, Yuning, Lee, Yong Jae
While existing large vision-language multimodal models focus on whole image understanding, there is a prominent gap in achieving region-specific comprehension. Current approaches that use textual coordinates or spatial encodings often fail to provide
Externí odkaz:
http://arxiv.org/abs/2312.00784
Autor:
Chen, Hongge, Chen, Zhao, Meyer, Gregory P., Park, Dennis, Vondrick, Carl, Shrivastava, Ashish, Chai, Yuning
We present SHIFT3D, a differentiable pipeline for generating 3D shapes that are structurally plausible yet challenging to 3D object detectors. In safety-critical applications like autonomous driving, discovering such novel challenging objects can off
Externí odkaz:
http://arxiv.org/abs/2309.05810
Balancing efficiency and accuracy is a long-standing problem for deploying deep learning models. The trade-off is even more important for real-time safety-critical systems like autonomous vehicles. In this paper, we propose an effective approach for
Externí odkaz:
http://arxiv.org/abs/2303.05078
Autor:
Brakerski, Zvika, Gheorghiu, Alexandru, Kahanamoku-Meyer, Gregory D., Porat, Eitan, Vidick, Thomas
A test of quantumness is a protocol that allows a classical verifier to certify (only) that a prover is not classical. We show that tests of quantumness that follow a certain template, which captures recent proposals such as (Kalai et al., 2022), can
Externí odkaz:
http://arxiv.org/abs/2303.01293
Autor:
Zhu, Daiwei, Kahanamoku-Meyer, Gregory D., Lewis, Laura, Noel, Crystal, Katz, Or, Harraz, Bahaa, Wang, Qingfeng, Risinger, Andrew, Feng, Lei, Biswas, Debopriyo, Egan, Laird, Gheorghiu, Alexandru, Nam, Yunseong, Vidick, Thomas, Vazirani, Umesh, Yao, Norman Y., Cetina, Marko, Monroe, Christopher
Publikováno v:
Nature Physics (2023)
Achieving quantum computational advantage requires solving a classically intractable problem on a quantum device. Natural proposals rely upon the intrinsic hardness of classically simulating quantum mechanics; however, verifying the output is itself
Externí odkaz:
http://arxiv.org/abs/2112.05156
Autor:
Dubois, Mathilde, Boulghobra, Doria, Rochebloine, Gilles, Pallot, Florian, Yehya, Marc, Bornard, Isabelle, Gayrard, Sandrine, Coste, Florence, Walther, Guillaume, Meyer, Gregory, Gaillard, Jean-Charles, Armengaud, Jean, Alpha-Bazin, Béatrice, Reboul, Cyril
Publikováno v:
In Redox Biology April 2024 70
