Anas Khan

[Anas Khan @anas2908k]

@SchmidhuberAI Hey Professor @SchmidhuberAI , we had an initial email conversation where you suggested PMAX, it’s super cool!!. I’d love your recommendations for more papers on self-supervised learning and world models. Looking forward to your response ([email protected]).

[IIT Bombay @iitbombay]

At the Indian Institute Of Technology Bombay, researchers are advancing clinically relevant AI for medical imaging with RadJEPA, a lightweight yet high-performance vision encoder for chest X-ray analysis. Developed at the Artificial Intelligence in Digital Health (AIDE) Lab, Koita Centre for Digital Health - KCDH (IIT Bombay), the work is led by Prof. Kshitij Jadhav, Assistant Professor, KCDH | Chief Project Coordinator, AI Centres of Excellence, MoE, GoI along with MS student Anas Khan.

RadJEPA was pre-trained on over 8 lakh unlabelled chest X-ray images, learning robust visual representations without relying on diagnostic annotations. Across multiple radiology tasks including disease classification, anatomical segmentation, and report generation, the model consistently outperformed existing radiology-specific and general-purpose vision models.

Notably, RadJEPA achieves these results with just 86 million parameters, outperforming models up to 10× larger, including a model developed by Microsoft trained under comparable data and computational settings. This demonstrates how carefully designed architectures from academic labs can rival and exceed large-scale industry models while using significantly fewer computational resources.

RadJEPA also shows strong robustness across datasets from different hospitals and scanners, a key requirement for real-world clinical deployment. Now released as an open-source model, RadJEPA is being explored globally, reinforcing IIT Bombay’s leadership in efficient, clinically grounded healthcare AI.
🔗 Project page: https://t.co/AYXQtJI5WZ

#IITBombay #HealthcareAI #MedicalImaging #EfficientAI #OpenScience #DigitalHealth

[Kshitij Jadhav (क्षितिज) 🇮🇳 @neurosapien]

We’re a small lab — but we punch well above our weight.

AIDE lab introduce RadJEPA — a chest X-ray vision encoder that outperforms Microsoft’s RAD-DINO and several other strong vision encoders.

Huge credit to @anas2908k , He pushed this through real constraints and adversity.