Skip to content

Author

Hitesh Sapkota

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.

Calibrated Knowledge Aggregation in Bayesian Mixture-of-Experts for Continual VQA

A calibrated Bayesian mixture-of-experts is proposed that trains parameter-efficient per-task adapters, learns routing by directly maximizing expected VQA utility, and marginalizes expert identity at inference via Bayesian aggregation in a unified answer space; an entropy penalty prevents the utility objective from col...

Mahsa Mozaffari, Hitesh Sapkota, Yu Kong et al. · 1 citation

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