Zobrazeno 1 - 10
of 20 171
pro vyhledávání: '"Padhi, A."'
The spectra of particles in disordered lattices can either be completely extended or localized or can be intermediate which hosts both the localized and extended states separated from each other. In this work, however, we show that in the case of a o
Externí odkaz:
http://arxiv.org/abs/2412.04344
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
Toxicity identification in online multimodal environments remains a challenging task due to the complexity of contextual connections across modalities (e.g., textual and visual). In this paper, we propose a novel framework that integrates Knowledge D
Externí odkaz:
http://arxiv.org/abs/2411.12174
Autor:
Lee, Bruce W., Padhi, Inkit, Ramamurthy, Karthikeyan Natesan, Miehling, Erik, Dognin, Pierre, Nagireddy, Manish, Dhurandhar, Amit
LLMs have shown remarkable capabilities, but precisely controlling their response behavior remains challenging. Existing activation steering methods alter LLM behavior indiscriminately, limiting their practical applicability in settings where selecti
Externí odkaz:
http://arxiv.org/abs/2409.05907
Autor:
Padhi, Inkit, Ramamurthy, Karthikeyan Natesan, Sattigeri, Prasanna, Nagireddy, Manish, Dognin, Pierre, Varshney, Kush R.
Aligning large language models (LLMs) to value systems has emerged as a significant area of research within the fields of AI and NLP. Currently, this alignment process relies on the availability of high-quality supervised and preference data, which c
Externí odkaz:
http://arxiv.org/abs/2408.10392
Training state-of-the-art (SOTA) deep learning models requires a large amount of data. The visual information present in the training data can be misused, which creates a huge privacy concern. One of the prominent solutions for this issue is perceptu
Externí odkaz:
http://arxiv.org/abs/2407.06570
Autor:
Padhi, Sudev Kumar, Ali, Sk. Subidh
Recent developments in Deep Neural Network (DNN) based watermarking techniques have shown remarkable performance. The state-of-the-art DNN-based techniques not only surpass the robustness of classical watermarking techniques but also show their robus
Externí odkaz:
http://arxiv.org/abs/2407.06552
Large language models (LLMs) have convincing performance in a variety of downstream tasks. However, these systems are prone to generating undesirable outputs such as harmful and biased text. In order to remedy such generations, the development of gua
Externí odkaz:
http://arxiv.org/abs/2407.06323
In this work, we investigate two salient chaotic features, namely Lyapunov exponent and butterfly velocity, in the context of an asymptotically Lifshitz black hole background with an arbitrary critical exponent. These features are computed using thre
Externí odkaz:
http://arxiv.org/abs/2406.18319
The landscape of fake media creation changed with the introduction of Generative Adversarial Networks (GAN s). Fake media creation has been on the rise with the rapid advances in generation technology, leading to new challenges in Detecting fake medi
Externí odkaz:
http://arxiv.org/abs/2406.18278