Vaidehi Patil

24 papers A* 2A 1B 1Journal 13Unranked 7
YearRankTypeTitle / Venue / Authors
2025 J jnl
Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns.
CoRR
Hanqi Xiao, Vaidehi Patil, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
MedForget: Hierarchy-Aware Multimodal Unlearning Testbed for Medical AI.
CoRR
Fengli Wu, Vaidehi Patil, Jaehong Yoon, Yue Zhang, Mohit Bansal
2025 A* conf
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation.
ICLR
Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal
2025 J jnl
The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration.
CoRR
Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning.
CoRR
Vaidehi Patil, Elias Stengel-Eskin, Mohit Bansal
2025 J jnl
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation.
CoRR
Vaidehi Patil, Yi-Lin Sung, Peter Hase, Jie Peng, Tianlong Chen, Mohit Bansal
2024 A* conf
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks.
ICLR
Vaidehi Patil, Peter Hase, Mohit Bansal
2024 — conf
REFINESUMM: Self-Refining MLLM for Generating a Multimodal Summarization Dataset.
ACL (1)
Vaidehi Patil, Leonardo F. R. Ribeiro, Mengwen Liu, Mohit Bansal, Markus Dreyer
2024 J jnl
SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation.
CoRR
Jaehong Yoon, Shoubin Yu, Vaidehi Patil, Huaxiu Yao, Mohit Bansal
2024 J jnl
Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation.
Trans. Mach. Learn. Res.
Vaidehi Patil, Yi-Lin Sung, Peter Hase, Jie Peng, Tianlong Chen, Mohit Bansal
2023 J jnl
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks.
CoRR
Vaidehi Patil, Peter Hase, Mohit Bansal
2023 — conf
Debiasing Multimodal Models via Causal Information Minimization.
EMNLP (Findings)
Vaidehi Patil, Adyasha Maharana, Mohit Bansal
2023 J jnl
Debiasing Multimodal Models via Causal Information Minimization.
CoRR
Vaidehi Patil, Adyasha Maharana, Mohit Bansal
2023 A conf
GEMS: Scene Expansion using Generative Models of Graphs.
WACV
Rishi Agarwal, Tirupati Saketh Chandra, Vaidehi Patil, Aniruddha Mahapatra, Kuldeep Kulkarni, Vishwa Vinay
2023 — conf
Safe to Approach: Insights on Autonomous Vehicle Interaction Protocols with First Responders.
HRI (Companion)
Seong Hee Lee, Vaidehi Patil, Nicholas Britten, Avram Block, Aryaman Pandya, Malte F. Jung, Paul Schmitt
2023 B conf
The Road Ahead: Advancing Interactions between Autonomous Vehicles, Pedestrians, and Other Road Users.
RO-MAN
Avram Block, Swapna Joshi, Wilbert Tabone, Aryaman Pandya, Seonghee Lee, Vaidehi Patil, Nicholas Britten, Paul Schmitt
2022 — conf
Characterization of a Meso-Scale Wearable Robot for Bathing Assistance.
ROBIO
Fukang Liu, Vaidehi Patil, Zackory Erickson, Fatma Zeynep Temel
2022 J jnl
Characterization of a Meso-Scale Wearable Robot for Bathing Assistance.
CoRR
Fukang Liu, Vaidehi Patil, Zackory Erickson, Fatma Zeynep Temel
2022 J jnl
GEMS: Scene Expansion using Generative Models of Graphs.
CoRR
Rishi Agarwal, Tirupati Saketh Chandra, Vaidehi Patil, Aniruddha Mahapatra, Kuldeep Kulkarni, Vishwa Vinay
2022 — conf
Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages.
ACL (1)
Vaidehi Patil, Partha P. Talukdar, Sunita Sarawagi
2022 J jnl
Overlap-based Vocabulary Generation Improves Cross-lingual Transfer Among Related Languages.
CoRR
Vaidehi Patil, Partha P. Talukdar, Sunita Sarawagi
2021 — conf
Detecting Document Versions and Their Ordering in a Collection.
WISE (2)
Natwar Modani, Anurag Maurya, Gaurav Verma, Inderjeet Nair, Vaidehi Patil, Anirudh Kanfade
2021 — conf
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study.
ACL/IJCNLP (1)
Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil, Abhijeet Awasthi, Partha P. Talukdar, Sunita Sarawagi
2021 J jnl
Exploiting Language Relatedness for Low Web-Resource Language Model Adaptation: An Indic Languages Study.
CoRR
Yash Khemchandani, Sarvesh Mehtani, Vaidehi Patil, Abhijeet Awasthi, Partha P. Talukdar, Sunita Sarawagi