Zobrazeno 1 - 10
of 40
pro vyhledávání: '"Agarwal, Anmol"'
Autor:
Agrawal, Amey, Agarwal, Anmol, Kedia, Nitin, Mohan, Jayashree, Kundu, Souvik, Kwatra, Nipun, Ramjee, Ramachandran, Tumanov, Alexey
Serving large language models (LLMs) in production can incur substantial costs, which has prompted recent advances in inference system optimizations. Today, these systems are evaluated against conventional latency and throughput metrics (eg. TTFT, TB
Externí odkaz:
http://arxiv.org/abs/2407.07000
Autor:
Deshpande, Ajinkya, Agarwal, Anmol, Shet, Shashank, Iyer, Arun, Kanade, Aditya, Bairi, Ramakrishna, Parthasarathy, Suresh
LLMs have demonstrated significant potential in code generation tasks, achieving promising results at the function or statement level across various benchmarks. However, the complexities associated with creating code artifacts like classes, particula
Externí odkaz:
http://arxiv.org/abs/2405.01573
Autor:
Agarwal, Anmol, Priyadarshi, Pratyush, Sinha, Shiven, Gupta, Shrey, Jangra, Hitkul, Kumaraguru, Ponnurangam, Garimella, Kiran
In this paper, we tackle the complex task of analyzing televised debates, with a focus on a prime time news debate show from India. Previous methods, which often relied solely on text, fall short in capturing the multimodal essence of these debates.
Externí odkaz:
http://arxiv.org/abs/2402.12629
Autor:
Agarwal, Anmol, Gupta, Shrey, Bonagiri, Vamshi, Gaur, Manas, Reagle, Joseph, Kumaraguru, Ponnurangam
Publikováno v:
45th European Conference on Information Retrieval, ECIR 2023
Information Disguise (ID), a part of computational ethics in Natural Language Processing (NLP), is concerned with best practices of textual paraphrasing to prevent the non-consensual use of authors' posts on the Internet. Research on ID becomes impor
Externí odkaz:
http://arxiv.org/abs/2311.05018
Publikováno v:
NeurIPS Workshop on Generative AI for Education (GAIED), 2023
Responding to the thousands of student questions on online QA platforms each semester has a considerable human cost, particularly in computing courses with rapidly growing enrollments. To address the challenges of scalable and intelligent question-an
Externí odkaz:
http://arxiv.org/abs/2311.02775
Autor:
Nanwani, Laksh, Agarwal, Anmol, Jain, Kanishk, Prabhakar, Raghav, Monis, Aaron, Mathur, Aditya, Murthy, Krishna, Hafez, Abdul, Gandhi, Vineet, Krishna, K. Madhava
Publikováno v:
IEEE RO-MAN 2023
Humans have a natural ability to perform semantic associations with the surrounding objects in the environment. This allows them to create a mental map of the environment, allowing them to navigate on-demand when given linguistic instructions. A natu
Externí odkaz:
http://arxiv.org/abs/2305.12363
Autor:
Agarwal, Anmol, Gupta, Jigar, Goel, Rahul, Upadhyay, Shyam, Joshi, Pankaj, Aravamudhan, Rengarajan
Extending semantic parsers to code-switched input has been a challenging problem, primarily due to a lack of supervised training data. In this work, we introduce CST5, a new data augmentation technique that finetunes a T5 model using a small seed set
Externí odkaz:
http://arxiv.org/abs/2211.07514
Autor:
Gupta, Shrey, Agarwal, Anmol, Gaur, Manas, Roy, Kaushik, Narayanan, Vignesh, Kumaraguru, Ponnurangam, Sheth, Amit
Conversational Agents (CAs) powered with deep language models (DLMs) have shown tremendous promise in the domain of mental health. Prominently, the CAs have been used to provide informational or therapeutic services to patients. However, the utility
Externí odkaz:
http://arxiv.org/abs/2205.13884
Autor:
Singh, Ashwin, Subramanian, Mallika, Agarwal, Anmol, Priyadarshi, Pratyush, Gupta, Shrey, Garimella, Kiran, Kumar, Sanjeev, Kumar, Ritesh, Garg, Lokesh, Arya, Erica, Kumaraguru, Ponnurangam
In the last two decades, ICTs have played a pivotal role in empowering rural populations in India by making knowledge more accessible. Digital Green (DG) is one such ICT that employs a participatory approach with smallholder farmers to produce instru
Externí odkaz:
http://arxiv.org/abs/2111.00052
Autor:
BHARDWAJ, CHHAYA1,2, AGARWAL, ANMOL3
Publikováno v:
Indiana Journal of Global Legal Studies. 2022, Vol. 29 Issue 2, p147-180. 34p.