ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Radu Soricut

Radu Soricut

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 5:57 AM AMS

11

papers

2,397

total citations

papers (11)

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

Connecting Vision and Language with Localized Narratives

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

On Scaling Up a Multilingual Vision and Language Model

PreSTU: Pre-Training for Scene-Text Understanding

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

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

NEURIPS 2021arXiv

Connecting Vision and Language With Video Localized Narratives

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

Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization