Author

Pooyan Fazli

h-index 15 View on Semantic Scholar

We have 1 of 58 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 Aug 2026

Video-FLAIR: Not Whether to Reason, But How

Video-FLAIR is introduced, a training framework that learns to select the appropriate reasoning mode for each query using reinforcement learning, and yields a supervision signal for learning adaptive reasoning without per-query annotations.

Yogesh Kulkarni, Pooyan Fazli · 0 citations