Vaidehi Patil's picture

Vaidehi Patil

vaidehi99

·

https://vaidehi99.github.io/

AI & ML interests

None yet

Recent Activity

upvoted a paper about 1 month ago

Harnessing LLM Agents with Skill Programs

upvoted a paper 2 months ago

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

submitted a paper 2 months ago

Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of Mind

View all activity

Organizations

None yet

commented 2 papers 9 months ago

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

Paper • 2509.24988 • Published Sep 29, 2025 • 1 •

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

Paper • 2509.14284 • Published Sep 16, 2025 • 2 •

New activity in vaidehi99/UnLOK-VQA about 1 year ago

Add link to paper and code

#2 opened about 1 year ago by

commented a paper about 1 year ago

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

Paper • 2505.01456 • Published May 1, 2025 • 2 •

commented a paper over 1 year ago

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

Paper • 2502.15082 • Published Feb 20, 2025 • 1 •