Jason Baldridge

9

Papers

1,380

Total Citations

Papers (9)

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

CoBIT: A Contrastive Bi-directional Image-Text Generation Model

Cross-Modal Contrastive Learning for Text-to-Image Generation

Less Is More: Generating Grounded Navigation Instructions From Landmarks

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

A New Path: Scaling Vision-and-Language Navigation With Synthetic Instructions and Imitation Learning

Transferable Representation Learning in Vision-and-Language Navigation

Pathdreamer: A World Model for Indoor Navigation

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing