Zobrazeno 1 - 10
of 8 074
pro vyhledávání: '"Murugesan, A. P."'
Autor:
Murugesan, Anitha, Wong, Isaac, Arias, Joaquín, Stroud, Robert, Varadarajan, Srivatsan, Salazar, Elmer, Gupta, Gopal, Bloomfield, Robin, Rushby, John
Assurance cases offer a structured way to present arguments and evidence for certification of systems where safety and security are critical. However, creating and evaluating these assurance cases can be complex and challenging, even for systems of m
Externí odkaz:
http://arxiv.org/abs/2408.11699
We consider the dimensional reduction of N=(2,0) conformal supergravity in six dimensions on a two-torus to N=4 conformal supergravity in four dimensions. At the level of kinematics, the six-dimensional Weyl multiplet is shown to reduce to a mixture
Externí odkaz:
http://arxiv.org/abs/2408.06026
We present ALT (ALignment with Textual feedback), an approach that aligns language models with user preferences expressed in text. We argue that text offers greater expressiveness, enabling users to provide richer feedback than simple comparative pre
Externí odkaz:
http://arxiv.org/abs/2407.16970
This paper addresses the critical issue of miscalibration in CLIP-based model adaptation, particularly in the challenging scenario of out-of-distribution (OOD) samples, which has been overlooked in the existing literature on CLIP adaptation. We empir
Externí odkaz:
http://arxiv.org/abs/2407.13588
Autor:
Gill, Sukhpal Singh, Golec, Muhammed, Hu, Jianmin, Xu, Minxian, Du, Junhui, Wu, Huaming, Walia, Guneet Kaur, Murugesan, Subramaniam Subramanian, Ali, Babar, Kumar, Mohit, Ye, Kejiang, Verma, Prabal, Kumar, Surendra, Cuadrado, Felix, Uhlig, Steve
Edge Artificial Intelligence (AI) incorporates a network of interconnected systems and devices that receive, cache, process, and analyse data in close communication with the location where the data is captured with AI technology. Recent advancements
Externí odkaz:
http://arxiv.org/abs/2407.04053
Autor:
Neehal, Nafis, Wang, Bowen, Debopadhaya, Shayom, Dan, Soham, Murugesan, Keerthiram, Anand, Vibha, Bennett, Kristin P.
CTBench is introduced as a benchmark to assess language models (LMs) in aiding clinical study design. Given study-specific metadata, CTBench evaluates AI models' ability to determine the baseline features of a clinical trial (CT), which include demog
Externí odkaz:
http://arxiv.org/abs/2406.17888
Interactive fiction games have emerged as an important application to improve the generalization capabilities of language-based reinforcement learning (RL) agents. Existing environments for interactive fiction games are domain-specific or time-consum
Externí odkaz:
http://arxiv.org/abs/2406.05872
Autor:
Do, Hyo Jin, Ostrand, Rachel, Weisz, Justin D., Dugan, Casey, Sattigeri, Prasanna, Wei, Dennis, Murugesan, Keerthiram, Geyer, Werner
While humans increasingly rely on large language models (LLMs), they are susceptible to generating inaccurate or false information, also known as "hallucinations". Technical advancements have been made in algorithms that detect hallucinated content b
Externí odkaz:
http://arxiv.org/abs/2405.20434
Autor:
Zhang, Shuai, Fernando, Heshan Devaka, Liu, Miao, Murugesan, Keerthiram, Lu, Songtao, Chen, Pin-Yu, Chen, Tianyi, Wang, Meng
This paper studies the transfer reinforcement learning (RL) problem where multiple RL problems have different reward functions but share the same underlying transition dynamics. In this setting, the Q-function of each RL problem (task) can be decompo
Externí odkaz:
http://arxiv.org/abs/2405.15920
Text-based reinforcement learning involves an agent interacting with a fictional environment using observed text and admissible actions in natural language to complete a task. Previous works have shown that agents can succeed in text-based interactiv
Externí odkaz:
http://arxiv.org/abs/2404.10174