| Influence Functions in Deep Learning Are Fragile S Basu, P Pope, S Feizi ICLR 2021, 2021 | 230 | 2021 |
| On Second-Order Group Influence Functions for Black-Box Predictions S Basu, X You, S Feizi ICML 2020, 2020 | 95 | 2020 |
| Genome wide analysis of W-box element in Arabidopsis thaliana reveals TGAC motif with genes down regulated by heat and salinity P Dhatterwal, S Basu, S Mehrotra, R Mehrotra Scientific Reports 9 (1), 1681, 2019 | 32 | 2019 |
| Strong Baselines for Parameter-Efficient Few-Shot Fine-Tuning S Basu, D Massiceti, S Xu Hu, S Feizi AAAI 2024, 2024 | 24 | 2024 |
| Membership Model Inversion Attacks for Deep Networks S Basu, R Izmailov, C Mesterharm NeurIPS 2019 Workshop, 2019 | 17 | 2019 |
| Localizing and Editing Knowledge in Text-to-Image Generative Models S Basu, N Zhao, V Morariu, S Feizi, V Manjunatha ICLR 2024, 2024 | 14 | 2024 |
| EditVal: Benchmarking Diffusion Based Text-Guided Image Editing Methods S Basu, M Saberi, S Bhardwaj, A Chegini, D Massiceti, M Sanjabi, SX Hu, ... arXiv, 2023 | 12 | 2023 |
| On Mechanistic Knowledge Localization in Text-to-Image Generative Models S Basu, K Rezaei, R Rossi, C Zhao, V Morariu, V Manjunatha, S Feizi ICML 2024, 2024 | 8 | 2024 |
| From RAGs to rich parameters: Probing how language models utilize external knowledge over parametric information for factual queries H Wadhwa, R Seetharaman, S Aggarwal, R Ghosh, S Basu, S Srinivasan, ... Blackbox NLP@ EMNLP 2024, 2024 | 6 | 2024 |
| Understanding Information Storage and Transfer in Multi-modal Large Language Models S Basu, M Grayson, C Morrison, B Nushi, S Feizi, D Massiceti NeurIPS 2024, 2024 | 6 | 2024 |
| Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks S Basu, M Stanley, JF Bronskill, S Feizi, D Massiceti ICLR 2023, 2023 | 6 | 2023 |
| Distilling Knowledge from Text-to-Image Generative Models Improves Visio-Linguistic Reasoning in CLIP S Basu, M Sanjabi, D Massiceti, S Xu Hu, S Feizi EMNLP 2024 (Main), 2023 | 5* | 2023 |
| On Surgical Fine-tuning for Language Encoders A Lodha, GV Belapurkar, S Chalkapurkar, Y Tao, S Basu, R Ghosh, ... EMNLP 2023, 2023 | 4 | 2023 |
| Strategies to improve few-shot learning for intent classification and slot-filling S Basu, A Sharaf, KIK Chong, A Fischer, V Rohra, M Amoake, ... NAACL 2022 (SUKI), 17-25, 2022 | 4 | 2022 |
| Topic Segmentation in the Wild: Towards Segmentation of Semi-Structured and Unstructured Chats R Ghosh, HS Kajal, S Kamath, D Shrivastava, S Basu, S Srinivasan NeurIPS 2022 Workshop, 2022 | 4 | 2022 |
| A survey of small language models C Van Nguyen, X Shen, R Aponte, Y Xia, S Basu, Z Hu, J Chen, M Parmar, ... arXiv preprint arXiv:2410.20011, 2024 | 3 | 2024 |
| Rethinking Artistic Copyright Infringements in the Era of Text-to-Image Generative Models M Moayeri, S Basu, S Balasubramanian, P Kattakinda, A Chengini, ... ICLR 2025 | Oral @ NeurIPS EvalEval 2024, 2024 | 3 | 2024 |
| Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP S Balasubramanian, S Basu, F Soheil NeurIPS 2024, 2024 | 2 | 2024 |
| Privacy leakage avoidance with switching ensembles R Izmailov, P Lin, C Mesterharm, S Basu MILCOM 2021-2021 IEEE Military Communications Conference (MILCOM), 981-986, 2021 | 2 | 2021 |
| IntCoOp: Interpretability-Aware Vision-Language Prompt Tuning SS Ghosal, S Basu, S Feizi, D Manocha EMNLP 2024 (Main), 2024 | 1 | 2024 |
Soheil FeiziUniversity of Maryland, College Park在 cs.umd.edu 的电子邮件经过验证