| 2026 | ACL | Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks. | Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu, Vaidehi Patil |
| 2025 | ICLR | SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation. | Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal |
| 2024 | ACL | REFINESUMM: Self-Refining MLLM for Generating a Multimodal Summarization Dataset. | Vaidehi Patil, Leonardo F. R. Ribeiro, Mengwen Liu, Mohit Bansal, Markus Dreyer |
| 2024 | ICLR | Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks. | Vaidehi Patil, Peter Hase, Mohit Bansal |
| 2023 | EMNLP | Debiasing Multimodal Models via Causal Information Minimization. | Vaidehi Patil, Adyasha Maharana, Mohit Bansal |
| 2023 | HRI | Safe to Approach: Insights on Autonomous Vehicle Interaction Protocols with First Responders. | Seong Hee Lee, Vaidehi Patil, Nicholas Britten, Avram Block, Aryaman Pandya, Malte F. Jung, Paul Schmitt |
| 2023 | WACV | GEMS: Scene Expansion using Generative Models of Graphs. | Rishi Agarwal, Tirupati Saketh Chandra, Vaidehi Patil, Aniruddha Mahapatra, Kuldeep Kulkarni, Vishwa Vinay |
| 2023 | RO-MAN | The Road Ahead: Advancing Interactions between Autonomous Vehicles, Pedestrians, and Other Road Users. | Avram Block, Swapna Joshi, Wilbert Tabone, Aryaman Pandya, Seonghee Lee, Vaidehi Patil, Nicholas Britten, Paul Schmitt |
| 2022 | ACL | Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages. | Vaidehi Patil, Partha P. Talukdar, Sunita Sarawagi |
| 2021 | ACL | Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study. | Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil, Abhijeet Awasthi, Partha P. Talukdar, Sunita Sarawagi |
| 2021 | WISE | Detecting Document Versions and Their Ordering in a Collection. | Natwar Modani, Anurag Maurya, Gaurav Verma, Inderjeet Nair, Vaidehi Patil, Anirudh Kanfade |