Sankalp Mittal — accepted AI-conference papers

2026

Text2Arch: A Dataset for Generating Scientific Architecture Diagrams from Natural Language Descriptions

Shivank Garg, Sankalp Mittal, Manish Gupta

ICLR 2026poster

Communicating complex system designs or scientific processes through text alone is inefficient and prone to ambiguity. A system that automatically generates scientific architecture diagrams from text with high semantic fidelity can be useful in multiple applications like enterprise architecture visu…

Cited by 0 Source ↗Scholar ↗

2024

Rethinking Robustness of Model Attributions

Sandesh Kamath, Sankalp Mittal, Amit Deshpande, Vineeth N Balasubramanian

AAAI 2024technical

For machine learning models to be reliable and trustworthy, their decisions must be interpretable. As these models find increasing use in safety-critical applications, it is important that not just the model predictions but also their explanations (as feature attributions) be robust to small human-i…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗