Xianhang Li

Computer Science · Physical Sciences

9h-index1.1kcitations44works30.62yr avg
OpenAlex↗ORCID↗Google Scholar↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(8), Human Pose and Action Recognition(8), Generative Adversarial Networks and Image Synthesis(7), Multimodal Machine Learning Applications(7), Domain Adaptation and Few-Shot Learning(5)

Publications44 total

OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
arXiv (Cornell University)·2026Open Access
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
ArXiv.org·2026Open Access
A deep learning framework for predicting ceramic viscosity during sintering
International Journal of Mechanical Sciences·2025
TransLibEval: Demystify Large Language Models' Capability in Third-party Library-targeted Code Translation
ArXiv.org·2025Open Access
OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning
arXiv (Cornell University)·2025Open Access
Efficient VideoMAE via Temporal Progressive Training
2025
OpenVision: A Fully-Open, Cost-Effective Family of Advanced Vision Encoders for Multimodal Learning
arXiv (Cornell University)·2025Open Access
An Innovative Adaptive-Dimension Accordion Honeycomb for Circumferential Deformation
Applied Sciences·2024Open Access
CLIPS: An Enhanced CLIP Framework for Learning with Synthetic Captions
arXiv (Cornell University)·2024Open Access
Accessing Elastic Properties of Porous Solid Oxide Fuel Cell Electrodes Using 2D Image-Based Discrete Element Modeling and Deep Learning
Acta Mechanica Solida Sinica·2024· 2 citedOpen Access
3D microstructure reconstruction and characterization of porous materials using a cross-sectional SEM image and deep learning
Heliyon·2024· 7 citedOpen Access
MedTrinity-25M: A Large-scale Multimodal Dataset with Multigranular Annotations for Medicine
arXiv (Cornell University)·2024· 7 citedOpen Access
TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers
Medical Image Analysis·2024· 713 citedOpen Access
Masked Autoencoders are Secretly Efficient Learners
2024
L2B: Learning to Bootstrap Robust Models for Combating Label Noise
2024· 8 cited
Revisiting Adversarial Training at Scale
2024· 13 cited
Autoregressive Pretraining with Mamba in Vision
arXiv (Cornell University)·2024Open Access
Medical Vision Generalist: Unifying Medical Imaging Tasks in Context
arXiv (Cornell University)·2024Open Access
Scaling White-Box Transformers for Vision
arXiv (Cornell University)·2024· 2 citedOpen Access
Brain Tumor Segmentation Through Supervoxel Transformer
2024· 1 cited
page 1 of 3Next →

Frequent Co-authors

Cihang Xie(23), Yuyin Zhou(17), Jieru Mei(11), Alan Yuille(9), Lei Xing(7), Qingyue Wei(5), Matthew P. Lungren(4), Hongru Zhu(4), Lequan Yu(4), Xuhao Liu(4), Zilin Yan(4), Yali Wang(3), Yu Qiao(3), Jieneng Chen(3), Kunchang Li(3), Shihao Zhou(3), Yuyin Zhou(3), Yongyi Lu(2), Qihang Yu(2), Xiangde Luo(2)