Anubhooti Jain

Hello World!



I’m a PhD scholar researching the reliability of vision in AI. In short, I investigate why models jump to conclusions so humans don’t have to.

My research sits somewhere between machine learning, human behaviour, and the art of asking, “wait, but why did the model do that?”

Advisors: Prof. Mayank Vatsa 🔗 and Prof. Richa Singh 🔗 at the IAB Lab 🔗, IIT Jodhpur

My Publications

  • Anubhooti Jain, Mayank Vatsa, Richa Singh. HumanBench: Two Heads, No Legs, But Mostly Human, the State of Generative Capabilities in T2I Models. In WACV 2026. 
  • Anubhooti Jain, Mayank Vatsa, Richa Singh. Words Over Pixels? Rethinking Vision in Multimodal Large Language Models. In IJCAI 2025. 🔗
  • Anubhooti Jain, Susim Roy, Kwanit Gupta, Mayank Vatsa, Richa Singh. Discerning the Chaos: Detecting Adversarial Perturbations while Disentangling Intentional from Unintentional Noise. In IJCB 2024. 🔗
  • Mayank Vatsa, Anubhooti Jain, Richa Singh. Adventures of Trustworthy Vision-Language Models: A Survey. In AAAI 2024. 🔗