ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Xiaohua Zhai

Xiaohua Zhai

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, 3:11 AM AMS

18

papers

11,309

total citations

papers (18)

MLP-Mixer: An all-MLP Architecture for Vision

NEURIPS 2021arXiv

Sigmoid Loss for Language Image Pre-Training

Scaling Vision Transformers

Big Transfer (BiT): General Visual Representation Learning

LiT: Zero-Shot Transfer With Locked-Image Text Tuning

Revisiting the Calibration of Modern Neural Networks

NEURIPS 2021arXiv

Simple Open-Vocabulary Object Detection with Vision Transformers

Knowledge Distillation: A Good Teacher Is Patient and Consistent

On Scaling Up a Multilingual Vision and Language Model

On Robustness and Transferability of Convolutional Neural Networks

Revisiting Neural Scaling Laws in Language and Vision

NEURIPS 2022arXiv

FlexiViT: One Model for All Patch Sizes

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design

NEURIPS 2023arXiv

Image Captioners Are Scalable Vision Learners Too

NEURIPS 2023arXiv

UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes

NEURIPS 2022arXiv

SILC: Improving Vision Language Pretraining with Self-Distillation

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

NEURIPS 2023arXiv

A Simple Single-Scale Vision Transformer for Object Detection and Instance Segmentation