Publications

Vaidehi Patil, Yi-Lin Sung, Peter Hase*, Jie Peng, Tianlong Chen, Mohit Bansal (2024). Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation. TMLR 2024.

PDF Cite

Vaidehi Patil, Leonardo F. R. Ribeiro, Mengwen Liu, Mohit Bansal, Markus Dreyer (2024). REFINESUMM: Self-Refining MLLM for Generating a Multimodal Summarization Dataset. ACL 2024.

PDF Cite Code Poster Slides Video

Vaidehi Patil, Adyasha Maharana, Mohit Bansal (2023). Debiasing Multimodal Models via Causal Information Minimization. In EMNLP 2023 Findings.

PDF Cite Code Poster Slides Video

Vaidehi Patil, Peter Hase*, Mohit Bansal (2023). Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks. ICLR 2024 (Spotlight).

PDF Cite Code Poster Slides Video Slideslive

Rishi Agarwal*, Tirupati Saketh Chandra*, Vaidehi Patil, Aniruddha Mahapatra*, Kuldeep Kulkarni, Vishwa Vinay (2022). GEMS: Scene Expansion using Generative Models of Graphs. In WACV 2023.

PDF Cite

Vaidehi Patil, Partha Talukdar, Sunita Sarawagi (2022). Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages. In ACL 2022.

PDF Cite Code Poster Slides Video

Natwar Modani, Anurag Maurya, Gaurav Verma, Inderjeet Nair, Vaidehi Patil, Anirudh Kanfade (2021). Detecting Document Versions and Their Ordering In a Collection. In WISE 2021.

PDF Cite Code

Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil, Abhijeet Awasthi, Partha Talukdar, Sunita Sarawagi (2021). Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study. In ACL 2021.

PDF Cite Code Poster Slides Video