Samyak Jain 个人学术档案 - 学术资源搜索

引用次数

	总计	2019 年至今
引用	140	140
h 指数	5	5
i10 指数	5	5

20212022202320241 19 44 73

开放获取的出版物数量

查看全部

3 篇文章

0 篇文章

可查看的文章

无法查看的文章

根据资助方的强制性开放获取政策

合著作者

Sravanti AddepalliPhD Student, Indian Institute of Science, Bangalore在 iisc.ac.in 的电子邮件经过验证
R. Venkatesh BabuCDS, Indian Institute of Science, Bangalore, India在 iisc.ac.in 的电子邮件经过验证
Gaurang SriramananPhD Student, University of Maryland, College Park在 umd.edu 的电子邮件经过验证
Ekdeep Singh LubanaHarvard / NTT在 fas.harvard.edu 的电子邮件经过验证
Hidenori TanakaGroup Leader, CBS-NTT Program in "Physics of Intelligence", Harvard University在 fas.harvard.edu 的电子邮件经过验证
David Scott KruegerUniversity Assistant Professor, University of Cambridge在 cam.ac.uk 的电子邮件经过验证
Robert KirkPhD Student, University College London在 ucl.ac.uk 的电子邮件经过验证
Tim RocktäschelProfessor of Artificial Intelligence at UCL, Open-Endedness Team Lead at Google DeepMind在 cs.ucl.ac.uk 的电子邮件经过验证
Edward GrefenstetteDirector of Research, Google DeepMind | Honorary Professor, UCL在 google.com 的电子邮件经过验证
Priyam DeyPhD Student, Indian Institute of Science, Bangalore在 iisc.ac.in 的电子邮件经过验证
Puneet K. DokaniaUniversity of Oxford | Five AI在 robots.ox.ac.uk 的电子邮件经过验证
Philip TorrProfessor, University of Oxford在 eng.ox.ac.uk 的电子邮件经过验证
Pratik ChattopadhyayAssistant Professor at Indian Institute of Technology (Banaras Hindu University), Varanasi在 iitbhu.ac.in 的电子邮件经过验证

关注

Samyak Jain

Undergrad at Indian Institute of Technology(BHU),Varanasi

在 itbhu.ac.in 的电子邮件经过验证 - 首页

AI Safety Mechanistic Interpretability Adversarial Robustness


标题按引用次数排序按年份排序按标题排序	引用次数引用次数	年份
Efficient and effective augmentation strategy for adversarial training S Addepalli, S Jain Advances in Neural Information Processing Systems 35, 1488-1501, 2022	44	2022
Scaling adversarial training to large perturbation bounds S Addepalli, S Jain, G Sriramanan, R Venkatesh Babu European Conference on Computer Vision, 301-316, 2022	40*	2022
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks S Jain, R Kirk, ES Lubana, RP Dick, H Tanaka, E Grefenstette, ... arXiv preprint arXiv:2311.12786, 2023	26	2023
Dart: Diversify-aggregate-repeat training improves generalization of neural networks S Jain, S Addepalli, PK Sahu, P Dey, RV Babu Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023	20	2023
Boosting adversarial robustness using feature level stochastic smoothing S Addepalli, S Jain, G Sriramanan, RV Babu Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2021	10	2021
What Makes and Breaks Safety Fine-tuning? Mechanistic Study S Jain, ES Lubana, K Oksuz, T Joy, PHS Torr, A Sanyal, PK Dokania arXiv preprint arXiv:2407.10264, 2024		2024
How does fine-tuning affect your model? Mechanistic analysis on procedural tasks S Jain, R Kirk, ES Lubana, RP Dick, H Tanaka, T Rocktäschel, ... R0-FoMo: Robustness of Few-shot and Zero-shot Learning in Large Foundation …, 0
Supplementary: DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks S Jain, S Addepalli, PK Sahu, P Dey, RV Babu
Supplementary Material: Towards Achieving Adversarial Robustness Beyond Perceptual Limits S Addepalli, S Jain, G Sriramanan, S Khare, RV Babu
Supplementary Material: Scaling Adversarial Training to Large Perturbation Bounds S Addepalli, S Jain, G Sriramanan, RV Babu
Supplementary Material: Boosting Adversarial Robustness using Feature Level Stochastic Smoothing S Addepalli, S Jain, G Sriramanan, RV Babu

系统目前无法执行此操作，请稍后再试。

文章 1–11

每年引用数

重复的引用

合并的引用

添加合著者合著作者

上传 PDF

关注此作者

引用次数

合著作者

引用