1 1

Vaidehi Patil

vaidehi99

https://vaidehi99.github.io/

AI & ML interests

None yet

Recent Activity

authored a paper 14 days ago

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

authored a paper 14 days ago

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

commented on a paper 14 days ago

UPCORE: Utility-Preserving Coreset Selection for Balanced Unlearning

View all activity

Organizations

None yet

Display a static welcome message

Running

InfoDeletionAttack

🏆

Display a welcome message for static spaces

models

None public yet

datasets 8

vaidehi99/UnLOK-VQA

Viewer • Updated 29 days ago • 505 • 75

vaidehi99/unl

Viewer • Updated Dec 12, 2024 • 1.01k • 8

vaidehi99/Acid_rain

Updated Oct 16, 2024 • 2

vaidehi99/combined_refusal_data

Viewer • Updated Oct 16, 2024 • 6.77k • 12

vaidehi99/RefineSumm

Viewer • Updated Oct 1, 2024 • 77k • 44 • 1

vaidehi99/MC_concepts_refusal

Viewer • Updated Sep 2, 2024 • 2.45k • 11

vaidehi99/LC_concepts_refusal

Viewer • Updated Sep 2, 2024 • 2k • 7

vaidehi99/HC_concepts_refusal

Viewer • Updated Sep 2, 2024 • 2.42k • 7

Vaidehi Patil

AI & ML interests

Recent Activity

Organizations

Papers 4

spaces 2 Sort: Recently updated

CausalInfoMin

InfoDeletionAttack

models

datasets 8 Sort: Recently updated

spaces 2

datasets 8