Makarand Tapaswi

Wadhwani AI, IIIT Hyderabad

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Computer Vision (1)Multimodal Models (1)

Frequent co-authors

Jona Ruthardt (1)Manu Gaur (1)Deva Ramanan (1)Yuki Asano (1)

Papers (1)

Apr 2, 2026

3w ago·also IIIT Hyderabad, University of Technology Nuremberg Point

Steerable Visual Representations

Forget salient cues – now you can *steer* visual representations in ViTs with language, focusing on any object you want without hurting overall performance.

Jona Ruthardt, Manu Gaur, Deva Ramanan +3

Computer Vision Multimodal Models

Search

Makarand Tapaswi

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)