Sadbhavana Babar
4 papers · 2021–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (10) π Conference Polyglot (3) π Interdisciplinary Bridge π Cross-Pollinator (15) π§ Keyword Pioneer
π£
Hot Topic Early Bird
β
The Questioner
Conferences
WACV (2)
ICLR (1)
NAACL (1)
Top co-authors
Keywords
safety alignment
(1)
adversarial attack
(1)
adversarial defense
(1)
virtual try-on
(1)
jailbreak attack
(1)
attention map
(1)
thin-plate spline
(1)
llm safety
(1)
weakly supervised object localization
(1)
large language model
(1)
channel-wise attention
(1)
texture inpainting
(1)
gradient inspection
(1)
quantized gradient
(1)
spatial self-attention
(1)
3d garment digitization
(1)
parametric template mesh
(1)
complementary region mining
(1)
Papers
Beyond Mere Token Analysis: A Hypergraph Metric Space Framework for Defending Against Socially Engineered LLM Attacks
ICLR 2025
SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection
NAACL 2025
Robust 3D Garment Digitization From Monocular 2D Images for 3D Virtual Try-On Systems
WACV 2022
Where to Look?: Mining Complementary Image Regions for Weakly Supervised Object Localization
WACV 2021