Zobrazeno 1 - 10
of 9 407
pro vyhledávání: '"Sontakke, A."'
Implementing image-based machine learning in agriculture is often limited by scarce data and annotations, making it hard to achieve high-quality model predictions. This study tackles the issue of postharvest quality assessment of bananas in decentral
Externí odkaz:
http://arxiv.org/abs/2411.16219
Foundational models are able to generate text outputs given prompt instructions and text, audio, or image inputs. Recently these models have been combined to perform tasks on video, such as video summarization. Such video foundation models perform pr
Externí odkaz:
http://arxiv.org/abs/2410.07405
Biological microswimmers, like euglena, deform their body shape to swim through tight confinements having length scales comparable to the microswimmer length scale. Recently, it was shown that self-propelling active droplets can also squeeze through
Externí odkaz:
http://arxiv.org/abs/2407.04324
Autor:
Kalluri, Shareef Babu, Singh, Prachi, Chowdhuri, Pratik Roy, Kulkarni, Apoorva, Baghel, Shikha, Hegde, Pradyoth, Sontakke, Swapnil, T, Deepak K, Prasanna, S. R. Mahadeva, Vijayasenan, Deepu, Ganapathy, Sriram
The DIarization of SPeaker and LAnguage in Conversational Environments (DISPLACE) 2024 challenge is the second in the series of DISPLACE challenges, which involves tasks of speaker diarization (SD) and language diarization (LD) on a challenging multi
Externí odkaz:
http://arxiv.org/abs/2406.09494
We propose Value Explicit Pretraining (VEP), a method that learns generalizable representations for transfer reinforcement learning. VEP enables learning of new tasks that share similar objectives as previously learned tasks, by learning an encoder f
Externí odkaz:
http://arxiv.org/abs/2312.12339
Autor:
Huang, Tianle, Sontakke, Nitish, Kumar, K. Niranjan, Essa, Irfan, Nikolaidis, Stefanos, Hong, Dennis W., Ha, Sehoon
Domain randomization (DR), which entails training a policy with randomized dynamics, has proven to be a simple yet effective algorithm for reducing the gap between simulation and the real world. However, DR often requires careful tuning of randomizat
Externí odkaz:
http://arxiv.org/abs/2310.10606
Autor:
Sontakke, Sumedh A, Zhang, Jesse, Arnold, Sébastien M. R., Pertsch, Karl, Bıyık, Erdem, Sadigh, Dorsa, Finn, Chelsea, Itti, Laurent
Reward specification is a notoriously difficult problem in reinforcement learning, requiring extensive expert supervision to design robust reward functions. Imitation learning (IL) methods attempt to circumvent these problems by utilizing expert demo
Externí odkaz:
http://arxiv.org/abs/2310.07899
Autor:
Chebotar, Yevgen, Vuong, Quan, Irpan, Alex, Hausman, Karol, Xia, Fei, Lu, Yao, Kumar, Aviral, Yu, Tianhe, Herzog, Alexander, Pertsch, Karl, Gopalakrishnan, Keerthana, Ibarz, Julian, Nachum, Ofir, Sontakke, Sumedh, Salazar, Grecia, Tran, Huong T, Peralta, Jodilyn, Tan, Clayton, Manjunath, Deeksha, Singht, Jaspiar, Zitkovich, Brianna, Jackson, Tomas, Rao, Kanishka, Finn, Chelsea, Levine, Sergey
In this work, we present a scalable reinforcement learning method for training multi-task policies from large offline datasets that can leverage both human demonstrations and autonomously collected data. Our method uses a Transformer to provide a sca
Externí odkaz:
http://arxiv.org/abs/2309.10150
Electronic invoicing is another area where blockchain technology is being used. Additionally, it has the power to alter how payments are made, invoices are issued, and transactions are validated. Using a blockchain-based invoicing system will enable
Externí odkaz:
http://arxiv.org/abs/2309.03303
Publikováno v:
International Journal of Computer Science Trends and Technology (IJCST) V11(4): Page(109-115) Jul - Aug 2023. ISSN: 2347-8578
Due to the widespread use of smartphones with high-quality digital cameras and easy access to a wide range of software apps for recording, editing, and sharing videos and images, as well as the deep learning AI platforms, a new phenomenon of 'faking'
Externí odkaz:
http://arxiv.org/abs/2309.03295