Aishwarya Agrawal

9

Papers

43

Total Citations

Papers (9)

Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding

Assessing and Learning Alignment of Unimodal Vision and Language Models

The Promise of RL for Autoregressive Image Editing

NeurIPS 2025arXiv

Don't Just Assume; Look and Answer: Overcoming Priors for Visual Question Answering

VQA: Visual Question Answering

Improving Automatic VQA Evaluation Using Large Language Models

CTRL-O: Language-Controllable Object-Centric Visual Representation Learning

Controlling Multimodal LLMs via Reward-guided Decoding

Overcoming Language Priors in Visual Question Answering with Adversarial Regularization