Scholar
Swadesh Swain
Google Scholar ID: MHH5khQAAAAJ
Indian Institute of Technology (IIT) Roorkee
Interpretability Alignment in AI
Robustness
3D computer vision
Generative AI
NLP
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
1
H-index
1
i10-index
0
Publications
3
Co-authors
0
Publications
3 items
Don't Judge an LLM Only by Its Activations: Discovering Suppressed Safety Features via Counterfactual Activation Potential
2026
Cited
0
Revisiting CroPA: A Reproducibility Study and Enhancements for Cross-Prompt Adversarial Transferability in Vision-Language Models
2025
Cited
0
Riemann Sum Optimization for Accurate Integrated Gradients Computation
arXiv.org · 2024
Cited
0
