Skip to content

Author

Makesh Narsimhan Sreedhar

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.

#artificial intelligence Review Aug 2026

Nemotron 3.5 Content Safety Moderator: A Compact Multimodal, Multilingual, and Reasoning Enabled Content Safety Moderator

Nemotron 3.5 CS demonstrates a practical coverage tradeoff: it adds image-conditioned and policy-conditioned moderation while remaining broadly competitive with specialized guard models, suggesting that compact vision-language moderators can serve as deployable front-line safety components.

Varun Singh, Anuj Doshi, Makesh Narsimhan Sreedhar et al. · 0 citations