Zobrazeno 1 - 10
of 29 964
pro vyhledávání: '"P. Finn"'
Autor:
Zhao, Tony Z., Tompson, Jonathan, Driess, Danny, Florence, Pete, Ghasemipour, Kamyar, Finn, Chelsea, Wahid, Ayzaan
Recent work has shown promising results for learning end-to-end robot policies using imitation learning. In this work we address the question of how far can we push imitation learning for challenging dexterous manipulation tasks. We show that a simpl
Externí odkaz:
http://arxiv.org/abs/2410.13126
Autor:
Mandati, Reddy, Anderson, Vladyslav, Chen, Po-chen, Agarwal, Ankush, Dokic, Tatjana, Barnard, David, Finn, Michael, Cromer, Jesse, Mccauley, Andrew, Tutaj, Clay, Dave, Neha, Besharati, Bobby, Barnett, Jamie, Krall, Timothy
In the past utilities relied on in-field inspections to identify asset defects. Recently, utilities have started using drone-based inspections to enhance the field-inspection process. We consider a vast repository of drone images, providing a wealth
Externí odkaz:
http://arxiv.org/abs/2410.11967
Autor:
Schmidtke, Finn, Vetter, Mathias
Given independent random variables $Y_1, \ldots, Y_n$ with $Y_i \in \{0,1\}$ we test the hypothesis whether the underlying success probabilities $p_i$ are constant or whether they are periodic with an unspecified period length of $r \ge 2$. The test
Externí odkaz:
http://arxiv.org/abs/2410.10203
Starting from an Enriques surface over $\mathbb{Q}(t)$ considered by Lafon, we give the first examples of smooth projective weakly special threefolds which fiber over the projective line in Enriques surfaces (resp. K3 surfaces) with nowhere reduced,
Externí odkaz:
http://arxiv.org/abs/2410.06643
In a previous paper, we realized a microwave network with symplectic symmetry simulating a spin 1/2 (Rehemanjiang et al. [Phys. Rev. Lett. 117, 064101 (2016)]), following a suggestion by Joyner et al. [Europhys. Lett. 107, 50004(2014))]. The network
Externí odkaz:
http://arxiv.org/abs/2410.07031
Autor:
Gustafsson, Ove Johan Ragnar, Wilkinson, Sean R., Bacall, Finn, Pireddu, Luca, Soiland-Reyes, Stian, Leo, Simone, Owen, Stuart, Juty, Nick, Fernández, José M., Grüning, Björn, Brown, Tom, Ménager, Hervé, Capella-Gutierrez, Salvador, Coppens, Frederik, Goble, Carole
The rising popularity of computational workflows is driven by the need for repetitive and scalable data processing, sharing of processing know-how, and transparent methods. As both combined records of analysis and descriptions of processing steps, wo
Externí odkaz:
http://arxiv.org/abs/2410.06941
Autor:
Dorrell, Will, Hsu, Kyle, Hollingsworth, Luke, Lee, Jin Hwa, Wu, Jiajun, Finn, Chelsea, Latham, Peter E, Behrens, Tim EJ, Whittington, James CR
Why do biological and artificial neurons sometimes modularise, each encoding a single meaningful variable, and sometimes entangle their representation of many variables? In this work, we develop a theory of when biologically inspired representations
Externí odkaz:
http://arxiv.org/abs/2410.06232
Autor:
Kopecz-Muller, Caroline, Gaunand, Clémence, Tran, Yvette, Labousse, Matthieu, Raphael, Elie, Salez, Thomas, Box, Finn, Mcgraw, Joshua D
We experimentally study the formation of surface patterns in grafted hydrogel films of nanometer-to-micrometer thicknesses during imbibition-driven swelling followed by evaporation-driven shrinking. Creases are known to form at the hydrogel surface d
Externí odkaz:
http://arxiv.org/abs/2410.05919
Autor:
Mahan, Dakota, Van Phung, Duy, Rafailov, Rafael, Blagden, Chase, Lile, Nathan, Castricato, Louis, Fränken, Jan-Philipp, Finn, Chelsea, Albalak, Alon
Reinforcement Learning from Human Feedback (RLHF) has greatly improved the performance of modern Large Language Models (LLMs). The RLHF process is resource-intensive and technically challenging, generally requiring a large collection of human prefere
Externí odkaz:
http://arxiv.org/abs/2410.12832
Autor:
Hung, Denise, Lemaux, Brian C., Cucciati, Olga, Forrest, Ben, Shah, Ekta A., Gal, Roy R., Giddings, Finn, Sikorski, Derek, Golden-Marx, Emmet, Lubin, Lori M., Hathi, Nimish, Zamorani, Giovanni, Bardelli, Sandro, Cassara, Letizia P., De Lucia, Gabriella, Fontanot, Fabio, Garilli, Bianca, Guaita, Lucia, Hirschmann, Michaela Monika, Lee, Kyoung-Soo, Newman, Andrew B., Ramakrishnan, Vandana, Vergani, Daniela, Xie, Lizhi, Zucca, Elena
The Charting Cluster Construction with VUDS and ORELSE (C3VO) survey is an ongoing imaging and spectroscopic campaign aiming to map out the growth of structure up to $z\sim5$ and was born from the combination of the VIMOS Ultra Deep Survey (VUDS) and
Externí odkaz:
http://arxiv.org/abs/2410.00237