Enrico Fini

5

Papers

69

Total Citations

Papers (5)

FlexTok: Resampling Images into 1D Token Sequences of Flexible Length

Improved baselines for vision-language pre-training

Multimodal Autoregressive Pre-training of Large Vision Encoders

On Large Multimodal Models as Open-World Image Classifiers

Scaling Laws for Native Multimodal Models