Zobrazeno 1 - 10
of 29
pro vyhledávání: '"Kant, Neel"'
Autor:
Mukherjee, Subhabrata, Gamble, Paul, Ausin, Markel Sanz, Kant, Neel, Aggarwal, Kriti, Manjunath, Neha, Datta, Debajyoti, Liu, Zhengliang, Ding, Jiayuan, Busacca, Sophia, Bianco, Cezanne, Sharma, Swapnil, Lasko, Rae, Voisard, Michelle, Harneja, Sanchay, Filippova, Darya, Meixiong, Gerry, Cha, Kevin, Youssefi, Amir, Buvanesh, Meyhaa, Weingram, Howard, Bierman-Lytle, Sebastian, Mangat, Harpreet Singh, Parikh, Kim, Godil, Saad, Miller, Alex
We develop Polaris, the first safety-focused LLM constellation for real-time patient-AI healthcare conversations. Unlike prior LLM works in healthcare focusing on tasks like question answering, our work specifically focuses on long multi-turn voice c
Externí odkaz:
http://arxiv.org/abs/2403.13313
Autor:
Wang, Zhilin, Dong, Yi, Zeng, Jiaqi, Adams, Virginia, Sreedhar, Makesh Narsimhan, Egert, Daniel, Delalleau, Olivier, Scowcroft, Jane Polak, Kant, Neel, Swope, Aidan, Kuchaiev, Oleksii
Existing open-source helpfulness preference datasets do not specify what makes some responses more helpful and others less so. Models trained on these datasets can incidentally learn to model dataset artifacts (e.g. preferring longer but unhelpful re
Externí odkaz:
http://arxiv.org/abs/2311.09528
Autor:
Roy, Rajarshi, Raiman, Jonathan, Kant, Neel, Elkin, Ilyas, Kirby, Robert, Siu, Michael, Oberman, Stuart, Godil, Saad, Catanzaro, Bryan
Publikováno v:
ACM/IEEE Design Automation Conference (DAC), 2021, pp. 853-858
In this work, we present a reinforcement learning (RL) based approach to designing parallel prefix circuits such as adders or priority encoders that are fundamental to high-performance digital design. Unlike prior methods, our approach designs soluti
Externí odkaz:
http://arxiv.org/abs/2205.07000
Autor:
Sachan, Devendra Singh, Patwary, Mostofa, Shoeybi, Mohammad, Kant, Neel, Ping, Wei, Hamilton, William L, Catanzaro, Bryan
Recent work on training neural retrievers for open-domain question answering (OpenQA) has employed both supervised and unsupervised approaches. However, it remains unclear how unsupervised and supervised methods can be used most effectively for neura
Externí odkaz:
http://arxiv.org/abs/2101.00408
Autor:
Shin, Richard, Kant, Neel, Gupta, Kavi, Bender, Christopher, Trabucco, Brandon, Singh, Rishabh, Song, Dawn
The goal of program synthesis is to automatically generate programs in a particular language from corresponding specifications, e.g. input-output behavior. Many current approaches achieve impressive results after training on randomly generated I/O ex
Externí odkaz:
http://arxiv.org/abs/1912.12345
Deep reinforcement learning (RL) policies are known to be vulnerable to adversarial perturbations to their observations, similar to adversarial examples for classifiers. However, an attacker is not usually able to directly modify another agent's obse
Externí odkaz:
http://arxiv.org/abs/1905.10615
Multi-emotion sentiment classification is a natural language processing (NLP) problem with valuable use cases on real-world data. We demonstrate that large-scale unsupervised language modeling combined with finetuning offers a practical solution to t
Externí odkaz:
http://arxiv.org/abs/1812.01207
Autor:
Kant, Neel
In recent years, deep learning has made tremendous progress in a number of fields that were previously out of reach for artificial intelligence. The successes in these problems has led researchers to consider the possibilities for intelligent systems
Externí odkaz:
http://arxiv.org/abs/1802.02353
Publikováno v:
Journal of Failure Analysis & Prevention; Jun2023, Vol. 23 Issue 3, p1114-1126, 13p
Humans have always dreamed of automating laborious physical and intellectual tasks, but the latter has proved more elusive than naively suspected. Seven decades of systematic study of Artificial Intelligence have witnessed cycles of hubris and despai
Externí odkaz:
https://library.oapen.org/handle/20.500.12657/57384