Author

Nenad Banfic

1 paper indexed here

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.

#machine learning Preprint Sep 2026

HeadGuard: Selective Head Protection for Low-Bit VLM KV-Cache Quantization

Evaluated through simulated quantization, HeadGuard offers a composable way to improve low-bit VLM accuracy without replacing the underlying quantizer.

Nenad Banfic · 0 citations