百晓学者学者目录

张少锋

副教授、教授，中国科学技术大学

精选作品

期刊论文

2026

Pathwise Test-Time Correction for Autoregressive Long Video Generation

Xunzhi Xiang, Zixuan Duan, Guiyu Zhang, Haiyu Zhang, Zhe Gao, Junta Wu, Shaofeng Zhang, Tengfei Wang, Qi Fan, Cheng Guo

Lecture notes in computer science

DOI

2026

EvoTok: A Unified Image Tokenizer via Residual Latent Evolution for Visual Understanding and Generation

Yan Li, Ning Liao, Xiangyu Zhao, Shaofeng Zhang, Xiaoxing Wang, Yifan Yang, Junchi Yan, Xue Yang

Lecture notes in computer science

DOI

2026

GRADE: Benchmarking Discipline-Informed Reasoning in Image Editing

Mingxin Liu, Ziqian Fan, Zhaokai Wang, Leyao Gu, Zirun Zhu, Yiguo He, Yuchen Yang, Changyao Tian, Xiangyu Zhao, Ning Liao, Shaofeng Zhang, Qibing Ren, Zhihang Zhong, Xuanhe Zhou, Junchi Yan, Xue Yang

Lecture notes in computer science

DOI

2026

PhyEditBench: A Real-World Multi-stage Benchmark for Physics-Aware Image Editing

Shengbin Guo, Shaokang He, Chaoyue Meng, Shengpeng Xiao, Xunzhi Xiang, Shaofeng Zhang, Qi Fan

Lecture notes in computer science

DOI

2026

xHC: Expanded Hyper-Connections

Xiang-Dong Zhang, Xiao-Han Qin, Su-Nan Zou, Tuo Dai, Xiao-Ming Shi, Huai-Jin Wu, Ye-Bin Yang, Zhuo Xia, Shaofeng Zhang, Lin Yao, Yu-Liang Liu, Yu Cheng, Jun-Chi Yan

arXiv.org

DOI

2026

ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving

Zhi-Yuan Zhang, Yanlun Peng, Jia-Ning Zhang, Xian-Da Guo, Ze-Han Huang, Haoran Liu, Qi-Feng Li, Shaofeng Zhang, Xiao-Song Jia, Jun-Chi Yan

arXiv.org

DOI

2026

NITP: Next Implicit Token Prediction for LLM Pre-training

Xiang-Dong Zhang, Debing Zhang, Shaofeng Zhang, Xiao-Han Qin, Yu Cheng, Jun-Chi Yan

arXiv.org

DOI

2026

Bench2Drive-Robust: Benchmarking Closed-Loop Autonomous Driving under Deployment Perturbations

Zhiyuan Zhang, Zhenghao Jin, Yanlun Peng, Xian-Da Guo, Haoran Liu, Shaofeng Zhang, Xingjun Ma, Zu-Xuan Wu, Jun-Chi Yan, Xiao-Song Jia, Yu-Gang Jiang

arXiv.org

DOI

2025

Point2RBox-v2: Rethinking Point-supervised Oriented Object Detection with Spatial Layout Among Instances

Yi Yu, Bo-Tao Ren, Pei-Yuan Zhang, Ming-Xin Liu, Junwei Luo, Shaofeng Zhang, Fei-Peng Da, Jun-Chi Yan, Xue Yang

Computer Vision and Pattern Recognition

DOI

2025

EasyOutPainter: One Step Image Outpainting With Both Continuous Multiple and Resolution

Shaofeng Zhang, Qiang Zhou, Zhi-Bin Wang, Hao Li, Jun Yan

IEEE Transactions on Pattern Analysis and Machine Intelligence

DOI

2025

Dual-Branch Center-Surrounding Contrast: Rethinking Contrastive Learning for 3D Point Clouds

Shaofeng Zhang, Xuanqi Chen, Xiang-Dong Zhang, Sitong Wu, Jun Yan

arXiv.org

DOI

2025

Towards More Diverse and Challenging Pre-Training for Point Cloud Learning: Self-Supervised Cross Reconstruction with Decoupled Views

Xiang-Dong Zhang, Shaofeng Zhang, Jun Yan

IEEE International Conference on Computer Vision

DOI

2025

Spatial Retrieval Augmented Autonomous Driving

Xiao-Song Jia, Chenhe Zhang, Yu-Le Jiang, Songbur Wong, Zhiyuan Zhang, Chen Chen, Shaofeng Zhang, Xu-Liu Zhou, Xue Yang, Jun-Chi Yan, Yu-Gang Jiang

arXiv.org

DOI

2025

Graph Pooling via Dropping Task-Irrelevant Nodes

Cheng Zhong, Shaofeng Zhang, Feng Zhu, Rui Zhao, Xiao-Kang Yang, Junchi Yan

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2025

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Xiang-Dong Zhang, Jiaqi Liao, Shaofeng Zhang, Fanqing Meng, Xiang Wan, Junchi Yan, Yu Cheng

Neural Information Processing Systems

DOI

2025

Building Type Classification Using CNN-Transformer Cross-Encoder Adaptive Learning From Very High Resolution Satellite Images

Shaofeng Zhang, Meng-Meng Li, Wu-Fan Zhao, Xiao-Qin Wang, Qun-Yong Wu

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing

DOI

2025

CR2PQ: Continuous Relative Rotary Positional Query for Dense Visual Representation Learning

Shaofeng Zhang, Qiang Zhou, Si-Tong Wu, Hao-Ru Tan, Zhi-Bin Wang, Jin-Fa Huang, Jun Yan

International Conference on Learning Representations

2024

Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation

Yan Li, Weiwei Guo, Xue Yang, Ning Liao, Shaofeng Zhang, Yi Yu, Wen-Xian Yu, Jun-Chi Yan

International Journal of Computer Vision

DOI

2024

View Crafting For Instance-Level Representation from Scene Images

Bin Liu, Yucheng Luo, Shaofeng Zhang, Zehuan Yuan, Changdong Xu, Bo-An Chen, Junchi Yan

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2024

PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders

Xiang-Dong Zhang, Shaofeng Zhang, Junchi Yan

Neural Information Processing Systems

DOI

2024

Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach

Shaofeng Zhang, Jin-Fa Huang, Qiang Zhou, Zhi-Bin Wang, Fan Wang, Jiebo Luo, Junchi Yan

International Conference on Learning Representations

DOI

2024

Building Type Classification Using Dual-Encoder Interaction Network from Very-High-Resolution Remote Sensing Images

Shaofeng Zhang, Meng-Meng Li, Kangkai Lou

2024 8th Asian Conference on Artificial Intelligence Technology (ACAIT)

DOI

2024

Urban Land Use Change Detection Using Siamese Graph Neural Networks from Bi-Temporal Very-High-Resolution Satellite Images

Kangkai Lou, Meng-Meng Li, Shaofeng Zhang

2024 8th Asian Conference on Artificial Intelligence Technology (ACAIT)

DOI

2024

Motion Control for Enhanced Complex Action Video Generation

Qiang Zhou, Shaofeng Zhang, Nianzu Yang, Ye Qian, Hao Li

arXiv.org

DOI

2023

RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension

Qiang Zhou, Chao-Hui Yu, Shaofeng Zhang, Si-Tong Wu, Zhi-Bin Wang, Fan Wang

arXiv.org

DOI

2023

Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining

Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan

International Conference on Learning Representations

2023

Patch-level Contrastive Learning via Positional Query for Visual Pre-training

Shaofeng Zhang, Qiang Zhou, Zhi-Bin Wang, Fan Wang, Junchi Yan

International Conference on Machine Learning

2023

REVO-LION: Evaluating and Refining Vision-Language Instruction Tuning Datasets

Ning Liao, Shaofeng Zhang, Ren-Qiu Xia, Bo Zhang, Min Cao, Yu Qiao, Junchi Yan

arXiv.org

DOI

2023

Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning

Shaofeng Zhang, Feng Zhu, Rui Zhao, Junchi Yan

International Conference on Learning Representations

DOI

2022

Align Representations with Base: A New Approach to Self-Supervised Learning

Shaofeng Zhang, Lyn Qiu, Feng Zhu, Junchi Yan, Hengrui Zhang, Rui Zhao, Hongyang Li, Xiao-Kang Yang

Computer Vision and Pattern Recognition

DOI

2022

Localized Contrastive Learning on Graphs

Hengrui Zhang, Qi-Tian Wu, Yu Wang, Shaofeng Zhang, Junchi Yan, Philip S. Yu

arXiv.org

DOI

2022

Self-supervised Learning of Visual Graph Matching

Chang Liu, Shaofeng Zhang, Xiao-Kang Yang, Junchi Yan

European Conference on Computer Vision

DOI

2022

DOTIN: Dropping Task-Irrelevant Nodes for GNNs

Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiao-Kang Yang

arXiv.org

DOI

2022

Zero-CL: Instance and Feature decorrelation for negative-free symmetric contrastive learning

Shaofeng Zhang, Feng Zhu, Junchi Yan, Rui Zhao, Xiao-Kang Yang

International Conference on Learning Representations

2022

M-Mix: Generating Hard Negatives via Multi-sample Mixing for Contrastive Learning

Shaofeng Zhang, Meng Liu, Junchi Yan, Hengrui Zhang, Lingxiao Huang, Xiao-Kang Yang, Pinyan Lu

Knowledge Discovery and Data Mining

DOI

2020

Fooled by Imagination: Adversarial Attack to Image Captioning Via Perturbation in Complex Domain

Shaofeng Zhang, Zheng Wang, Xing Xu, Xiang Guan, Yang Yang

IEEE International Conference on Multimedia and Expo

DOI

2020

The Diversified Ensemble Neural Network

Shaofeng Zhang, Meng Liu, Junchi Yan

Neural Information Processing Systems

预印本

2026

Point as Skeleton: Accumulated Point Cloud Enhanced Autoregressive Generation for Closed-Loop Autonomous Driving Simulation

Songbur Wong, Xiaosong Jia, Junqi You, Bo Zhang, Pei Xu, Renqiu Xia, Y L Qiu, Shaofeng Zhang, Zelin Zhao, Xuechao Yan, Yuchen Zhou, Yurui Chen, Wen Guo, Hang Xu, Junchi Yan

arXiv (Cornell University)

DOI

2026

Enhancing Video Physical Consistency via Role-aware Joint Training and Modality-decoupled Denoising

Guangting Zheng, Haojing Chen, Hao Li, Jingtao Zhang, Zhen Yang, Xiaosong Jia, Xue Yang, Shaofeng Zhang, Yanyong Zhang

arXiv (Cornell University)

DOI

2026

Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling

Yihang Wu, Yihang Sun, Shaofeng Zhang, Zuxuan Wu, Junchi Yan, Xiaosong Jia, Yu-Gang Jiang

arXiv (Cornell University)

DOI

2026

Prompt-Free Universal Region Proposal Network

Qihong Tang, Changhan Liu, Shaofeng Zhang, Wenbin Li, Qi Fan, Yang Gao

arXiv (Cornell University)

DOI

2026

PointAlign: Feature-Level Alignment Regularization for 3D Vision-Language Models

Yuanhao Su, Shaofeng Zhang, Xiaosong Jia, Qi Fan

arXiv (Cornell University)

DOI

研究方向

图像与三维场景表征学习生成式模型与三维场景理解多模态融合感知大模型具身智能

此主页由公开资料整理，尚未经学者本人认领。