3 papers
cs.LG2026
How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects
Abhivansh Gupta, Simardeep Singh, Advika Sinha +2
Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a principled understanding of how…
cs.CV2026
Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models
Shreyansh Modi, Akshat Tomar, Aarush Aggarwal
Unconditional diffusion models offer powerful generative priors, yet steering them toward aesthetically enhanced outputs remains largely unexplored. We show that h-space patching,…
cs.LG2026
OmniPatch: A Universal Adversarial Patch for ViT-CNN Cross-Architecture Transfer in Semantic Segmentation
Aarush Aggarwal, Akshat Tomar, Amritanshu Tiwari +1
Robust semantic segmentation is crucial for safe autonomous driving, yet deployed models remain vulnerable to black-box adversarial attacks when target weights are unknown. Most ex…