Zobrazeno 1 - 10
of 15 250
pro vyhledávání: '"P., KARTHIKEYAN"'
Autor:
Tanveer, Md Sayed, Patel, Dhruvik, Schweiger, Hunter E., Abu-Bonsrah, Kwaku Dad, Watmuff, Brad, Azadi, Azin, Pryshchep, Sergey, Narayanan, Karthikeyan, Puleo, Christopher, Natarajan, Kannathal, Mostajo-Radji, Mohammed A., Kagan, Brett J., Wang, Ge
With the recent advancements in artificial intelligence, researchers and industries are deploying gigantic models trained on billions of samples. While training these models consumes a huge amount of energy, human brains produce similar outputs (alon
Externí odkaz:
http://arxiv.org/abs/2412.14112
Autor:
Karthikeyan, Akash, Pant, Yash Vardhan
Offline reinforcement learning has shown tremendous success in behavioral planning by learning from previously collected demonstrations. However, decision-making in multitask missions still presents significant challenges. For instance, a mission mig
Externí odkaz:
http://arxiv.org/abs/2412.08565
Autor:
Wei, Dennis, Padhi, Inkit, Ghosh, Soumya, Dhurandhar, Amit, Ramamurthy, Karthikeyan Natesan, Chang, Maria
Training data attribution (TDA) is the task of attributing model behavior to elements in the training data. This paper draws attention to the common setting where one has access only to the final trained model, and not the training algorithm or inter
Externí odkaz:
http://arxiv.org/abs/2412.03906
Publikováno v:
Addepalli, S., Varun, Y., Suggala, A., Shanmugam, K. and Jain, P., Does Safety Training of LLMs Generalize to Semantically Related Natural Prompts?. In Neurips Safe Generative AI Workshop 2024
Large Language Models (LLMs) are known to be susceptible to crafted adversarial attacks or jailbreaks that lead to the generation of objectionable content despite being aligned to human preferences using safety fine-tuning methods. While the large di
Externí odkaz:
http://arxiv.org/abs/2412.03235
Autor:
Varun, Yerram, Madhavan, Rahul, Addepalli, Sravanti, Suggala, Arun, Shanmugam, Karthikeyan, Jain, Prateek
Publikováno v:
Varun, Y., Madhavan, R., Addepalli, S., Suggala, A., Shanmugam, K., & Jain, P. Time-Reversal Provides Unsupervised Feedback to LLMs. In The Thirty-Eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
Large Language Models (LLMs) are typically trained to predict in the forward direction of time. However, recent works have shown that prompting these models to look back and critique their own generations can produce useful feedback. Motivated by thi
Externí odkaz:
http://arxiv.org/abs/2412.02626
Autor:
Karthikeyan, Akash, Pant, Yash Vardhan
Despite recent advances in learning-based behavioral planning for autonomous systems, decision-making in multi-task missions remains a challenging problem. For instance, a mission might require a robot to explore an unknown environment, locate the go
Externí odkaz:
http://arxiv.org/abs/2412.00293
Multi-modal Large Language Models (MLLMs) are gaining significant attention for their ability to process multi-modal data, providing enhanced contextual understanding of complex problems. MLLMs have demonstrated exceptional capabilities in tasks such
Externí odkaz:
http://arxiv.org/abs/2412.00102
Autor:
Miehling, Erik, Desmond, Michael, Ramamurthy, Karthikeyan Natesan, Daly, Elizabeth M., Dognin, Pierre, Rios, Jesus, Bouneffouf, Djallel, Liu, Miao
Building pluralistic AI requires designing models that are able to be shaped to represent a wide range of value systems and cultures. Achieving this requires first being able to evaluate the degree to which a given model is capable of reflecting vari
Externí odkaz:
http://arxiv.org/abs/2411.12405
Our work aims to minimize interaction in secure computation due to the high cost and challenges associated with communication rounds, particularly in scenarios with many clients. In this work, we revisit the problem of secure aggregation in the singl
Externí odkaz:
http://arxiv.org/abs/2410.22303
Autor:
Dasgupta, Arpan, Jain, Gagan, Suggala, Arun, Shanmugam, Karthikeyan, Tambe, Milind, Taneja, Aparna
Mobile health (mHealth) programs face a critical challenge in optimizing the timing of automated health information calls to beneficiaries. This challenge has been formulated as a collaborative multi-armed bandit problem, requiring online learning of
Externí odkaz:
http://arxiv.org/abs/2410.21405