Radu Soricut

12

Papers

301

Total Citations

Papers (12)

On Scaling Up a Multilingual Vision and Language Model

Cold-Start Reinforcement Learning with Softmax Policy Gradient

NeurIPS 2017arXiv

Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts

Connecting Vision and Language With Video Localized Narratives

Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization

Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting

PreSTU: Pre-Training for Scene-Text Understanding

Connecting Vision and Language with Localized Narratives

PACTran: PAC-Bayesian Metrics for Estimating the Transferability of Pretrained Models to Classification Tasks

Telling the What While Pointing to the Where: Multimodal Queries for Image Retrieval

Omni-SMoLA: Boosting Generalist Multimodal Models with Soft Mixture of Low-rank Experts

Bridging the Gap Between Practice and PAC-Bayes Theory in Few-Shot Meta-Learning