Skip to content

Author

Mohd. Azfar

We have 2 of 4 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

SPARK: Representation-Level KV Memory Alignment for Safer Vision-Language Models

SPARK is introduced, a two-stage framework for targeted KV-memory repair that reduces multimodal attack success while preserving general capability and suggests that multimodal jailbreak behavior can be substantially mitigated by selectively repairing intervention-relevant KV subspaces at prefill.

Mohd. Azfar, I. Khan · 0 citations
Preprint Aug 2026

Robust Lightweight Deep Learning Models for Oral Cancer Screening

The optimisation of lightweight deep learning models for smartphone-based oral cancer screening is presented and it is confirmed that with targeted architectural selection and streamlined optimisation, interpretable and robust lightweight AI models exhibit high potential for edge deployment to enable automated triage i...

Siddhant Bharadwaj, Aakash Shedsale, T. Subramanya et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.