Vaidehi Patil

vaidehi99's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored 2 papers 3 months ago

Generalized Correctness Models: Learning Calibrated and Model-Agnostic Correctness Predictors from Historical Patterns

Paper • 2509.24988 • Published Sep 29

The Sum Leaks More Than Its Parts: Compositional Privacy Risks and Mitigations in Multi-Agent Collaboration

Paper • 2509.14284 • Published Sep 16 • 2

authored a paper 8 months ago

Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluation

Paper • 2505.01456 • Published May 1 • 2

authored 2 papers 10 months ago

SAFREE: Training-Free and Adaptive Guard for Safe Text-to-Image And Video Generation

Paper • 2410.12761 • Published Oct 16, 2024

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

Paper • 2502.15082 • Published Feb 20 • 1

authored 2 papers about 2 years ago

Debiasing Multimodal Models via Causal Information Minimization

Paper • 2311.16941 • Published Nov 28, 2023 • 1

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Paper • 2309.17410 • Published Sep 29, 2023 • 4