Posts by Collection

portfolio

publications

Sample-Efficient Deep Learning for COVID-19 Diagnosis Based on CT Scans

Preprint, 2020

Xuehai He*, Xingyi Yang*, Shanghang Zhang*, Jinyu Zhao, Yichen Zhang, Eric Xing, Pengtao Xie * Equally contributed

Paper

COVID-CT-Dataset: A CT Scan Dataset about COVID-19

Preprint, 2020

Xingyi Yang, Xuehai He, Jinyu Zhao, Yichen Zhang, Shanghang Zhang, Pengtao Xie

Paper Code

Transfer Learning or Self-supervised Learning? A Tale of Two Pretraining Paradigms

Preprint, 2020

Xingyi Yang*, Xuehai He∗,Yuxiao Liang, Yue Yang, Shanghang Zhang, Pengtao Xie * Equally contributed

Paper Code

Single View Metrology in the Wild

16th European Conference on Computer Vision (ECCV2020), 2020

Rui Zhu, Xingyi Yang, Yannick Hold-Geoffroy, Federico Perazzi, Jonathan Eisenmann, Kalyan Sunkavalli, Manmohan Chandraker

Paper Code Project

Kalman Optimizer for Consistent Gradient Descent

2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2021), 2021

Xingyi Yang

Paper Code Slides Video

DSRNA: Differentiable Search of Robust Neural Architectures

2021 Conference on Computer Vision and Pattern Recognition (CVPR2021), 2021

Ramtin Hosseini, Xingyi Yang, Pengtao Xie

Paper

Writing by Memorizing: Hierarchical Retrieval-based Medical Report Generation

The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL2021), (Long Oral), 2021

Xingyi Yang, Muchao Ye, Quanzeng You and Fenglong Ma

Paper

On the Generation of Medical Dialogues for COVID-19

The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL2021), long paper, 2021

Wenmian Yang, Guangtao Zeng, Bowen Tan, Zeqian Ju, Subrato Chakravorty, Xuehai He, Shu Chen, Xingyi Yang, Qingyang Wu, Zhou Yu, Eric Xing, Pengtao Xie

Paper Code

Neural Point Process for Learning Spatiotemporal Event Dynamics

Conference on Learning for Dynamics and Control (L4DC), 2022

Zihao Zhou, Xingyi Yang, Ryan Rossi, Handong Zhao, Rose Yu

Paper Code

Learning with Recoverable Forgetting

European Conference on Computer Vision (ECCV), 2022

Jingwen Ye, Fu Yifang, Jie Song, Xingyi Yang, Songhua Liu, Xin Jin, Mingli Song, Xinchao Wang

arXiv Code

Factorizing Knowledge in Neural Networks

European Conference on Computer Vision (ECCV), 2022

Xingyi Yang, Jingwen Ye, Xinchao Wang

Paper Code Poster Video

Dataset Distillation via Factorization

Neural Information Processing Systems (NeurIPS), 2022

Songhua Liu, Kai Wang, Xingyi Yang, Jingwen Ye, Xinchao Wang

Paper arXiv Code

Deep Model Reassembly

Neural Information Processing Systems (NeurIPS), (Paper Award Nomination), 2022

Xingyi Yang, Daquan Zhou, Songhua Liu, Jingwen Ye, Xinchao Wang

Paper arXiv Code Project Video

Towards Stochastic Gradient Variance Reduction by Solving a Filtering Problem

Tiny Papers @ ICLR 2023, 2023

Xingyi Yang

Paper Code

Distribution Shift Inversion for Out-of-Distribution Generalization

Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Runpeng Yu, Songhua Liu, Xingyi Yang, Xinchao Wang

Details

Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detection

Conference on Computer Vision and Pattern Recognition (CVPR), (Highlight), 2023

Xinjiang Wang*, Xingyi Yang*, Shilong Zhang, Yijiang Li, Litong Feng, Shijie Fang, Chengqi Lyu, Kai Chen, Wayne Zhang (* Equally Contributed)

Paper Code Project

Diffusion Probabilistic Model Made Slim

Conference on Computer Vision and Pattern Recognition (CVPR), 2023

Xingyi Yang, Daquan Zhou, Jiashi Feng, Xinchao Wang

arXiv

SG-Former: Self-guided Transformer with Evolving Token Reallocation

Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Sucheng Ren, Xingyi Yang, Songhua Liu, Xinchao Wang

Details

Diffusion Model as Representation Learner

Proceedings of IEEE/CVF International Conference on Computer Vision (ICCV), 2023

Xingyi Yang, Xinchao Wang

Details

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

2023 Conference on Neural Information Processing (NeurIPS), 2023

Jiaqi Wang, Xingyi Yang, Suhan Cui, Liwei Che, Lingjuan Lyu, Dongkuan Xu, Fenglong Ma

Details

StyDeSty: Min-Max Stylization and Destylization for Single Domain Generalization

International Conference on Machine Learning (ICML), 2024

Songhua Liu, Xin Jin, Xingyi Yang, Jingwen Ye, Xinchao Wang

Details

Relation Rectification in Diffusion Model

Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Yinwei Wu, Xingyi Yang, Xinchao Wang

Paper Code Project

Unsegment Anything by Simulating Deformation

Conference on Computer Vision and Pattern Recognition (CVPR), 2024

Jiahao Lu, Xingyi Yang, Xinchao Wang

Details

Vista3D: Unravel the 3D Darkside of a Single Image

European Conference on Computer Vision (ECCV), 2024

Qiuhong Shen, Xingyi Yang, Michael Bi Mi, Xinchao Wang

arXiv Code

FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

European Conference on Computer Vision (ECCV), 2024

Qiuhong Shen, Xingyi Yang, Xinchao Wang

arXiv Code

Neural Metamorphosis

European Conference on Computer Vision (ECCV), 2024

Xingyi Yang, Xinchao Wang

Paper Project

Language Model as Visual Explainer

Neural Information Processing Systems (NeurIPS), 2024

Xingyi Yang, Xinchao Wang

arXiv

Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling

Annual AAAI Conference on Artificial Intelligence (AAAI), 2025

Hanyang Kong, Xingyi Yang, Xinchao Wang

arXiv

GFlow: Recovering 4D World from Monocular Video

Annual AAAI Conference on Artificial Intelligence (AAAI), 2025

Shizun Wang, Xingyi Yang, Qiuhong Shen, Zhenxiang Jiang, Xinchao Wang

arXiv Project

GraphBridge: Towards Arbitrary Transfer Learning in GNNs

International Conference on Learning Representations (ICLR), 2025

Li Ju, Xingyi Yang, Qi Li, Xinchao Wang

arXiv Code

Kolmogorov-Arnold Transformer

International Conference on Learning Representations (ICLR), 2025

Xingyi Yang, Xinchao Wang

arXiv Code

CoSER: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation

Computer Vision and Pattern Recognition (CVPR), (Highlight), 2025

Bonan Li, Zicheng Zhang, Xingyi Yang, Xinchao Wang

Paper

Generative Sparse-View Gaussian Splatting

Computer Vision and Pattern Recognition (CVPR), 2025

Hanyang Kong, Xingyi Yang, Xinchao Wang

Paper

Few-shot Implicit Function Generation via Equivariance

Computer Vision and Pattern Recognition (CVPR), (Highlight), 2025

Suizhi Huang, Xingyi Yang, Hongtao Lu, Xinchao Wang

Paper Code Project

Hash3D: Training-free Acceleration for 3D Generation

Computer Vision and Pattern Recognition (CVPR), 2025

Xingyi Yang, Songhua Liu, Xinchao Wang

Paper Code Project

Mixture of Experts Made Intrinsically Interpretable

International Conference on Machine Learning (ICML), 2025

Xingyi Yang, Constantin Venhoff, Ashkan Khakzar ,Christian Schroeder de Witt ,Puneet K. Dokania, Adel Bibi, Philip Torr

Paper

RogSplat: Robust Gaussian Splatting via Generative Priors

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Hanyang Kong, Xingyi Yang, Xinchao Wang

Details

C4D: 4D Made from 3D through Dual Correspondences

IEEE/CVF International Conference on Computer Vision (ICCV), 2025

Shizun Wang, Zhenxiang Jiang, Xingyi Yang, Xinchao Wang

arXiv Project

OminiControl: Minimal and Universal Control for Diffusion Transformer

IEEE/CVF International Conference on Computer Vision (ICCV), (Highlight), 2025

Zhenxiong Tan, Songhua Liu, Xingyi Yang, Qiaochu Xue, and Xinchao Wang

Paper Code Demo

TreeSplat: Mergeable Tree for Deformable Gaussian Splatting

Neural Information Processing Systems (NeurIPS), 2025

Qiuhong Shen, Xingyi Yang, Xinchao Wang

Paper

1000+ FPS 4D Gaussian Splatting for Dynamic Scene Rendering

Neural Information Processing Systems (NeurIPS), 2025

Yuheng Yuan, Qiuhong Shen, Xingyi Yang, Xinchao Wang

Paper Project

Image Editing As Programs with Diffusion Models

Neural Information Processing Systems (NeurIPS), 2025

Yujia Hu, Songhua Liu, ZhenXiong Tan, Xingyi Yang, Xinchao Wang

Paper Code

Test3R: Learning to Reconstruct 3D at Test Time

Neural Information Processing Systems (NeurIPS), 2025

Yuheng Yuan, Qiuhong Shen, Shizun Wang, Xingyi Yang, Xinchao Wang

Paper Code Project

Minute-Long Videos with Dual Parallelisms

AAAI Conference on Artificial Intelligence (AAAI), 2026

Zeqing Wang, Bowen Zheng, Xingyi Yang, Zhenxiong Tan, Yuecong Xu, Xinchao Wang

Paper Code Project

DirMoE: Dirichlet-routed Mixture of Experts

International Conference on Learning Representations (ICLR), 2026

Amirhossein Vahidi, Hesam Asadollahzadeh, Navid Akhavan Attar, Marie Moullet, Kevin Ly, Xingyi Yang, Mohammad Lotfollahi

Paper arXiv

SparseD: Sparse Attention for Diffusion Language Models

International Conference on Learning Representations (ICLR), 2026

Zeqing Wang, Gongfan Fang, Xinyin Ma, Xingyi Yang^*, Xinchao Wang^* (^*Corresponding Author)

Paper Code

portfolio

publications

talks

teaching