Zobrazeno 1 - 10
of 920
pro vyhledávání: '"Dokania P"'
Autor:
Abe, S., Alekseev, I., Arai, T., Arihara, T., Arimoto, S., Babu, N., Baranov, V., Bartoszek, L., Berns, L., Bhattacharjee, S., Blondel, A., Boikov, A. V., Buizza-Avanzini, M., Capó, J., Cayo, J., Chakrani, J., Chong, P. S., Chvirova, A., Danilov, M., Davis, C., Davydov, Yu. I., Dergacheva, A., Dokania, N., Douqa, D., Doyle, T. A., Drapier, O., Eguchi, A., Elias, J., Fedorova, D., Fedotov, S., Ferlewicz, D., Fuji, Y., Furui, Y., Gendotti, A., Germer, A., Giannessi, L., Giganti, C., Glagolev, V., Hu, J., Iwamoto, K., Jakkapu, M., Jesús-Valls, C., Ji, J. Y., Jung, C. K., Kakuno, H., Kasetti, S. P., Kawaue, M., Khabibullin, M., Khotjantsev, A., Kikawa, T., Kikutani, H., Kobayashi, H., Kobayashi, T., Kodama, S., Kolupanova, M., Korzenev, A., Kose, U., Kudenko, Y., Kuribayashi, S., Kutter, T., Lachat, M., Lachner, K., Last, D., Latham, N., Silverio, D. Leon, Li, B., Li, W., Li, Z., Lin, C., Lin, L. S., Lin, S., Lux, T., Mahtani, K., Maret, L., Caicedo, D. A. Martinez, Martynenko, S., Matsubara, T., Mauger, C., McGrew, C., McKean, J., Mefodiev, A., Miller, E., Mineev, O., Moreno, A. L., Muñoz, A., Nakadaira, T., Nakagiri, K., Nguyen, V., Nicola, L., Noah, E., Nosek, T., Okinaga, W., Osu, L., Paolone, V., Parsa, S., Pellegrino, R., Ramirez, M. A., Reh, M., Ricco, C., Rubbia, A., Sakashita, K., Sallin, N., Sanchez, F., Schefke, T., Schloesser, C. M., Sgalaberna, D., Shvartsman, A., Skrobova, N., Speers, A. J., Suslov, I. A., Suvorov, S., Svirida, D., Tairafune, S., Tanigawa, H., Teklu, A., Tereshchenko, V. V., Tzanov, M., Vasilyev, I. I., Wallace, H. T., Whitney, N., Wood, K., Xu, Y. -h., Yang, G., Yershov, N., Yokoyama, M., Yoshimoto, Y., Zhao, X., Zheng, H., Zhu, T., Zilberman, P., Zimmerman, E. D.
The magnetised near detector (ND280) of the T2K long-baseline neutrino oscillation experiment has been recently upgraded aiming to satisfy the requirement of reducing the systematic uncertainty from measuring the neutrinonucleus interaction cross sec
Externí odkaz:
http://arxiv.org/abs/2410.24099
Autor:
Jain, Samyak, Lubana, Ekdeep Singh, Oksuz, Kemal, Joy, Tom, Torr, Philip H. S., Sanyal, Amartya, Dokania, Puneet K.
Safety fine-tuning helps align Large Language Models (LLMs) with human preferences for their safe deployment. To better understand the underlying factors that make models safe via safety fine-tuning, we design a synthetic data generation framework th
Externí odkaz:
http://arxiv.org/abs/2407.10264
Autor:
Rawat, Abhay, Dokania, Shubham, Srivastava, Astitva, Ahmed, Shuaib, Feng, Haiwen, Tallamraju, Rahul
Recent advancements in generative models have unlocked the capabilities to render photo-realistic data in a controllable fashion. Trained on the real data, these generative models are capable of producing realistic samples with minimal to no domain g
Externí odkaz:
http://arxiv.org/abs/2406.07840
Reliable usage of object detectors require them to be calibrated -- a crucial problem that requires careful attention. Recent approaches towards this involve (1) designing new loss functions to obtain calibrated detectors by training them from scratc
Externí odkaz:
http://arxiv.org/abs/2405.20459
When deploying a semantic segmentation model into the real world, it will inevitably encounter semantic classes that were not seen during training. To ensure a safe deployment of such systems, it is crucial to accurately evaluate and improve their an
Externí odkaz:
http://arxiv.org/abs/2402.16392
Autor:
Prabhu, Ameya, Sinha, Shiven, Kumaraguru, Ponnurangam, Torr, Philip H. S., Sener, Ozan, Dokania, Puneet K.
Continual learning has primarily focused on the issue of catastrophic forgetting and the associated stability-plasticity tradeoffs. However, little attention has been paid to the efficacy of continually learned representations, as representations are
Externí odkaz:
http://arxiv.org/abs/2402.08823
Referring Image Segmentation (RIS) - the problem of identifying objects in images through natural language sentences - is a challenging task currently mostly solved through supervised learning. However, while collecting referred annotation masks is a
Externí odkaz:
http://arxiv.org/abs/2310.13479
Combining the strengths of many existing predictors to obtain a Mixture of Experts which is superior to its individual components is an effective way to improve the performance without having to develop new architectures or train a model from scratch
Externí odkaz:
http://arxiv.org/abs/2309.14976
Pre-trained foundation models, due to their enormous capacity and exposure to vast amounts of data during pre-training, are known to have learned plenty of real-world concepts. An important step in making these pre-trained models effective on downstr
Externí odkaz:
http://arxiv.org/abs/2308.13320
Towards Building Self-Aware Object Detectors via Reliable Uncertainty Quantification and Calibration
The current approach for testing the robustness of object detectors suffers from serious deficiencies such as improper methods of performing out-of-distribution detection and using calibration metrics which do not consider both localisation and class
Externí odkaz:
http://arxiv.org/abs/2307.00934