Hexiang Hu

Affiliations

Google DeepMind

papers

2,218

total citations

papers (13)

Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities

ICCV 2023arXiv

citations

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

ICML 2024arXiv

citations

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

NEURIPS 2023arXiv

citations

Instruct-Imagen: Image Generation with Multi-modal Instruction

CVPR 2024arXiv

citations

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

NEURIPS 2021arXiv

citations

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

ICCV 2021arXiv

citations

PreSTU: Pre-Training for Scene-Text Understanding

ICCV 2023arXiv

citations

Scaling Inference Time Compute for Diffusion Models

CVPR 2025

citations

Hexiang Hu

Affiliations

papers (13)

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Learning the Best Pooling Strategy for Visual Semantic Embedding

On Scaling Up a Multilingual Vision and Language Model

Subject-driven Text-to-Image Generation via Apprenticeship Learning

UniIR: Training and Benchmarking Universal Multimodal Information Retrievers

Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

Instruct-Imagen: Image Generation with Multi-modal Instruction

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

PreSTU: Pre-Training for Scene-Text Understanding

Scaling Inference Time Compute for Diffusion Models

papers (13)

Few-Shot Learning via Embedding Adaptation With Set-to-Set Functions

Learning the Best Pooling Strategy for Visual Semantic Embedding

On Scaling Up a Multilingual Vision and Language Model

Subject-driven Text-to-Image Generation via Apprenticeship Learning

UniIR: Training and Benchmarking Universal Multimodal Information Retrievers

Open-domain Visual Entity Recognition: Towards Recognizing Millions of Wikipedia Entities

MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

Instruct-Imagen: Image Generation with Multi-modal Instruction

On Model Calibration for Long-Tailed Object Detection and Instance Segmentation

MosaicOS: A Simple and Effective Use of Object-Centric Images for Long-Tailed Object Detection

PreSTU: Pre-Training for Scene-Text Understanding

Scaling Inference Time Compute for Diffusion Models