Adaptive Meta-Learning for Robust Deepfake Detection: A Multi-Agent Framework to Data Drift and Model Generalization

Autor: P, Dinesh Srivasthav, Subudhi, Badri Narayan

Pioneering advancements in artificial intelligence, especially in genAI, have enabled significant possibilities for content creation, but also led to widespread misinformation and false content. The growing sophistication and realism of deepfakes is

Externí odkaz: http://arxiv.org/abs/2411.08148

Search for Extended GeV Sources in the Inner Galactic Plane

Autor: Abdollahi, S., Acero, F., Acharyya, A., Adelfio, A., Ajello, M., Baldini, L., Ballet, J., Bartolini, C., Gonzalez, J. Becerra, Bellazzini, R., Bissaldi, E., Bonino, R., Bruel, P., Cameron, R. A., Caraveo, P. A., Castro, D., Cavazzuti, E., Cheung, C. C., Cibrario, N., Ciprini, S., Cozzolongo, G., Orestano, P. Cristarella, Cuoco, A., Cutini, S., D'Ammando, F., Di Lalla, N., Dinesh, A., Di Venere, L., Domínguez, A., Fiori, A., Funk, S., Fusco, P., Gargano, F., Gasbarra, C., Gasparrini, D., Germani, S., Giacchino, F., Giglietto, N., Giliberti, M., Giordano, F., Giroletti, M., Green, D., Grenier, I. A., Guillemot, L., Guiriec, S., Gupta, R., Hashizume, M., Hays, E., Hewitt, J. W., Horan, D., Hou, X., Kayanoki, T., Kuss, M., Laviron, A., Lemoine-Goumard, M., Liguori, A., Li, J., Liodakis, I., Loizzo, P., Longo, F., Loparco, F., Lorusso, L., Lovellette, M. N., Lubrano, P., Maldera, S., Malyshev, D., Martí-Devesa, G., Martin, P., Mazziotta, M. N., Mereu, I., Michelson, P. F., Mirabal, N., Mitthumsiri, W., Mizuno, T., Monti-Guarnieri, P., Monzani, M. E., Morselli, A., Moskalenko, I. V., Negro, M., Omodei, N., Orienti, M., Orlando, E., Paneque, D., Panzarini, G., Persic, M., Pesce-Rollins, M., Pillera, R., Porter, T. A., Rainò, S., Rando, R., Razzano, M., Reimer, A., Reimer, O., Bernal, M. Rocamora, Sánchez-Conde, M., Parkinson, P. M. Saz, Serini, D., Sgrò, C., Siskind, E. J., Smith, D. A., Spandre, G., Spinelli, P., Strong, A. W., Suson, D. J., Tajima, H., Thayer, J. B., Torres, D. F., Valverde, J., Wadiasingh, Z., Wood, K., Zaharijas, G.

The recent detection of extended $\gamma$-ray emission around middle-aged pulsars is interpreted as inverse-Compton scattering of ambient photons by electron-positron pairs escaping the pulsar wind nebula, which are confined near the system by unclea

Externí odkaz: http://arxiv.org/abs/2411.07162

Vision Language Models are In-Context Value Learners

Autor: Ma, Yecheng Jason, Hejna, Joey, Wahid, Ayzaan, Fu, Chuyuan, Shah, Dhruv, Liang, Jacky, Xu, Zhuo, Kirmani, Sean, Xu, Peng, Driess, Danny, Xiao, Ted, Tompson, Jonathan, Bastani, Osbert, Jayaraman, Dinesh, Yu, Wenhao, Zhang, Tingnan, Sadigh, Dorsa, Xia, Fei

Predicting temporal progress from visual trajectories is important for intelligent robots that can learn, adapt, and improve. However, learning such progress estimator, or temporal value function, across different tasks and domains requires both a la

Externí odkaz: http://arxiv.org/abs/2411.04549

New physics effects in semileptonic $\bar{B_s} \to K^{*+}(\to K\pi) \ell^- \bar{\nu}_\ell$ decay

Autor: Khan, Shabana, Kumar, Dinesh

In this work, we analyze the new physics effects in semileptonic decay $\bar{B_s} \to K^{*+}(\to K\pi) \ell^- \bar{\nu}_\ell$ induced by the $b \to u \ell \nu_{\ell}$ quark level transition. We consider the vector, axial vector, scalar, pseudoscalar

Externí odkaz: http://arxiv.org/abs/2411.03238

Task-Oriented Hierarchical Object Decomposition for Visuomotor Control

Autor: Qian, Jianing, Li, Yunshuang, Bucher, Bernadette, Jayaraman, Dinesh

Publikováno v: CoRL 2024

Good pre-trained visual representations could enable robots to learn visuomotor policy efficiently. Still, existing representations take a one-size-fits-all-tasks approach that comes with two important drawbacks: (1) Being completely task-agnostic, t

Externí odkaz: http://arxiv.org/abs/2411.01284