Ashwath Vaithinathan Aravindan

ashwath-vaithina's activity

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

authored 3 papers 4 months ago

Do VLMs Have Bad Eyes? Diagnosing Compositional Failures via Mechanistic Interpretability

Paper • 2508.16652 • Published Aug 20, 2025

Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillation

Paper • 2508.18235 • Published Aug 20, 2025

Code-Driven Planning in Grid Worlds with Large Language Models

Paper • 2505.10749 • Published May 15, 2025