Zobrazeno 1 - 10
of 27 531
pro vyhledávání: '"Bedi"'
Autor:
Arief Bramanto Wicaksono Putra, Rheo Malani, Bedi Suprapty, Achmad Fanany Onnilita Gaffar, Roman Voliansky
Publikováno v:
Knowledge Engineering and Data Science, Vol 6, Iss 1, Pp 1-14 (2023)
Video compression is used for storage or bandwidth efficiency in clip video information. Video compression involves encoders and decoders. Video compression uses intra-frame, inter-frame, and block-based methods. Video compression compresses nearby f
Externí odkaz:
https://doaj.org/article/ef4a4a6c3f4048069d1e72d765b65494
Autor:
Chen Vicky, Jones Morgan, Cohen Lauren, Yang Wilson, Bedi Jasman, Mohan Helen M., Apte Sameer S., Larach José Tomas, Flood Michael, Heriot Alexander, Kong Joseph, Warrier Satish
Publikováno v:
Pleura and Peritoneum, Vol 7, Iss 4, Pp 159-167 (2022)
Small bowel adenocarcinoma (SBA) with peritoneal metastasis (PM) is rare and despite treatment with systemic chemotherapy, the prognosis is poor. However, there is emerging evidence that cytoreductive surgery (CRS) with hyperthermic intraperitoneal c
Externí odkaz:
https://doaj.org/article/63fcfa35586945a88b29bceac4619668
Publikováno v:
IROS 2024
While LLMs are proficient at processing text in human conversations, they often encounter difficulties with the nuances of verbal instructions and, thus, remain prone to hallucinate trust in human command. In this work, we present TrustNavGPT, an LLM
Externí odkaz:
http://arxiv.org/abs/2408.01867
Autor:
Ding, Mucong, Chakraborty, Souradip, Agrawal, Vibhu, Che, Zora, Koppel, Alec, Wang, Mengdi, Bedi, Amrit, Huang, Furong
Reinforcement Learning from Human Feedback (RLHF) is a key method for aligning large language models (LLMs) with human preferences. However, current offline alignment approaches like DPO, IPO, and SLiC rely heavily on fixed preference datasets, which
Externí odkaz:
http://arxiv.org/abs/2406.15567
Embodied Question Answering (EQA) is an important problem, which involves an agent exploring the environment to answer user queries. In the existing literature, EQA has exclusively been studied in single-agent scenarios, where exploration can be time
Externí odkaz:
http://arxiv.org/abs/2406.10918
Autor:
Singh, Utsav, Chakraborty, Souradip, Suttle, Wesley A., Sadler, Brian M., Namboodiri, Vinay P, Bedi, Amrit Singh
Learning control policies to perform complex robotics tasks from human preference data presents significant challenges. On the one hand, the complexity of such tasks typically requires learning policies to perform a variety of subtasks, then combinin
Externí odkaz:
http://arxiv.org/abs/2406.10892
Autor:
Mulyanto Mulyanto, Bedi Suprapty, Arief Bramanto Wicaksono Putra, Achmad Fanany Onnilita Gaffar
Publikováno v:
Jurnal Informatika, Vol 15, Iss 1, Pp 28-44 (2021)
In addition to the focus of research selected as a Final Project material, the selection of lecturers as student's supervisor becomes very important. The lecturer's competence related to the focus of student research and the supervising style of lect
Externí odkaz:
https://doaj.org/article/e5bd1cc05a494be7ab75c87d89b39f7e
Publikováno v:
E3S Web of Conferences, Vol 430, p 01263 (2023)
Finishing of cylindrical surfaces in nano-scale roughness level is important to improve the surface structure of various industrial components. The nanofinishing not only enhances the surface quality but also improve the durability and reliability th
Externí odkaz:
https://doaj.org/article/9f3ca961f51f4b9d9dce45ae0b68a32d
Autor:
Chakraborty, Souradip, Ghosal, Soumya Suvra, Yin, Ming, Manocha, Dinesh, Wang, Mengdi, Bedi, Amrit Singh, Huang, Furong
Aligning foundation models is essential for their safe and trustworthy deployment. However, traditional fine-tuning methods are computationally intensive and require updating billions of model parameters. A promising alternative, alignment via decodi
Externí odkaz:
http://arxiv.org/abs/2405.20495
Standard federated learning (FL) approaches are vulnerable to the free-rider dilemma: participating agents can contribute little to nothing yet receive a well-trained aggregated model. While prior mechanisms attempt to solve the free-rider dilemma, n
Externí odkaz:
http://arxiv.org/abs/2405.13879