Maya Varma

Symbal: Detecting Systematic Misalignments in Model-Generated Captions

Activation Matters: Adaptive and Activated Negative Labels for OOD Detection with Vision-Language Models

Attention Head Entropy of LLMs Predicts Answer Correctness

LieRE: Lie Rotational Positional Encodings

TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models

Preference fine-tuning for factuality in chest X-ray interpretation models without human feedback