Author

Kaushik Roy

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.

#small language model Preprint Sep 2026

FAVE: Foveated Adaptive Visual Encoding for Efficient Fine-Grained Visual Understanding

FAVE (Foveated Adaptive Visual Encoding), a lightweight variable-resolution ViT that encodes externally selected regions at high acuity while preserving native geometry, is introduced and integrated as a complementary local branch in FastVLM.

Amitangshu Mukherjee, Kaushik Roy · 0 citations