Soheil Feizi
University of Maryland
H-index: 39
North America-United States
Top articles of Soheil Feizi
Title | Journal | Author(s) | Publication Date |
|---|---|---|---|
Temporal Robustness against Data Poisoning | Advances in Neural Information Processing Systems | Wenxiao Wang Soheil Feizi | 2024/2/13 |
What do we learn from inverting CLIP models? | arXiv preprint arXiv:2403.02580 | Hamid Kazemi Atoosa Chegini Jonas Geiping Soheil Feizi Tom Goldstein | 2024/3/5 |
Data-Centric Debugging: mitigating model failures via targeted image retrieval | arXiv preprint arXiv:2211.09859 | Sahil Singla Atoosa Malemir Chegini Mazda Moayeri Soheil Feiz | 2022/11/17 |
Fast Adversarial Attacks on Language Models In One GPU Minute | arXiv preprint arXiv:2402.15570 | Vinu Sankar Sadasivan Shoumik Saha Gaurang Sriramanan Priyatham Kattakinda Atoosa Chegini | 2024/2/23 |
Spuriosity rankings: Sorting data to measure and mitigate biases | Advances in Neural Information Processing Systems | Mazda Moayeri Wenxiao Wang Sahil Singla Soheil Feizi | 2024/2/13 |
Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models | arXiv preprint arXiv:2404.08030 | Mazda Moayeri Samyadeep Basu Sriram Balasubramanian Priyatham Kattakinda Atoosa Chengini | 2024/4/11 |
Exploring Geometry of Blind Spots in Vision Models | Advances in Neural Information Processing Systems | Sriram Balasubramanian Gaurang Sriramanan Vinu Sankar Sadasivan Soheil Feizi | 2024/2/13 |
Measuring self-supervised representation quality for downstream classification using discriminative features | Proceedings of the AAAI Conference on Artificial Intelligence | Neha Kalibhat Kanika Narang Hamed Firooz Maziar Sanjabi Soheil Feizi | 2024/3/24 |
Diffused Redundancy in Pre-trained Representations | Advances in Neural Information Processing Systems | Vedant Nanda Till Speicher John Dickerson Krishna Gummadi Soheil Feizi | 2024/2/13 |
Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning | Proceedings of the AAAI Conference on Artificial Intelligence | Samyadeep Basu Shell Hu Daniela Massiceti Soheil Feizi | 2024/3/24 |
Online Advertisements with LLMs: Opportunities and Challenges | Soheil Feizi MohammadTaghi Hajiaghayi Keivan Rezaei Suho Shin | 2023/11/11 | |
Towards Improved Input Masking for Convolutional Neural Networks | Sriram Balasubramanian Soheil Feizi | 2023 | |
Interpolated joint space adversarial training for robust and generalizable defenses | IEEE Transactions on Pattern Analysis and Machine Intelligence | Chun Pong Lau Jiang Liu Hossein Souri Wei-An Lin Soheil Feizi | 2023/6/19 |
Identifying interpretable subspaces in image representations | Neha Kalibhat Shweta Bhardwaj C Bayan Bruss Hamed Firooz Maziar Sanjabi | 2023/7/3 | |
PRIME: Prioritizing Interpretability in Failure Mode Extraction | arXiv preprint arXiv:2310.00164 | Keivan Rezaei Mehrdad Saberi Mazda Moayeri Soheil Feizi | 2023/9/29 |
Benchmarking Diffusion Based Text-Guided Image Editing Methods | Samyadeep Basu Mehrdad Saberi Shweta Bhardwaj Atoosa Chegini Daniela Massiceti | 2023/10/13 | |
Text2concept: Concept activation vectors directly from text | Mazda Moayeri Keivan Rezaei Maziar Sanjabi Soheil Feizi | 2023 | |
Provable Robustness for Streaming Models with a Sliding Window | arXiv preprint arXiv:2303.16308 | Aounon Kumar Vinu Sankar Sadasivan Soheil Feizi | 2023/3/28 |
Text-to-concept (and back) via cross-model alignment | Mazda Moayeri Keivan Rezaei Maziar Sanjabi Soheil Feizi | 2023/7/3 | |
Robustness of ai-image detectors: Fundamental limits and practical attacks | arXiv preprint arXiv:2310.00076 | Mehrdad Saberi Vinu Sankar Sadasivan Keivan Rezaei Aounon Kumar Atoosa Chegini | 2023/9/29 |
