Pushpak Bhattacharyya

Dual Distillation of Trajectory and Guidance Knowledge for Faster Inference in Conditional Masked Diffusion Language Models

Clinically Interpretable Rule–Guided Preference Optimization in Vision–Language Models for Radiology Report Generation

BEYOND SINGLE-AXIS FAIRNESS: LEARNING TO DETECT INTERSECTIONAL BIASES

SAVIOR: Sample-efficient Alignment of Vision-Language Models for OCR Representation

Languages Differ, Weaknesses Persist: Jailbreaking LLMs Across English and Indian Languages

MOMENTUM MEETS VIRALITY: A NOVEL METRIC FOR UNMASKING SOCIAL BIAS IN VIRAL TWEETS