Fartash Faghri

4

Papers

120

Total Citations

1

Affiliations

Affiliations

University of Toronto

Papers (4)

MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training

FastVLM: Efficient Vision Encoding for Vision Language Models

Proxy-FDA: Proxy-based Feature Distribution Alignment for Fine-tuning Vision Foundation Models without Forgetting

Knowledge Transfer from Vision Foundation Models for Efficient Training of Small Task-specific Models