Xue Yang

Assistant Professor, Ph.D. Supervisor

School of Automation and Intelligent Sensing, Shanghai Jiao Tong University

800 Dongchuan Road, Shanghai, 200240, China

📧 [email protected], [email protected], [email protected]


我正在寻找自驱力较强的攻读硕/博士(2027年保研、拿到2026年及以后创智/中关村/河套等国家AI学院offer)的学生、实习生,与严骏驰教授共同指导,目标是在基础视觉、多模态大模型、空间智能等课题上做出有影响力的工作。请随时通过电子邮件与我联系。

Looking for self-motivated students (Master/Ph.D. 2027 spring & fall), interns to join us, co-supervised by Prof. Junchi Yan, with the goal of doing impactful work on the topic of Fundamental Vision, Multimodal Large Language Model, Spatial Intelligence, etc. Please do not hesitate to contact me via email.

🔑 Research Interests

My research interests include Fundamental Vision, Multimodal Large Language Model, Spatial Intelligence, etc.

📝 Short Biography

Xue Yang has published about 50 papers Citations: 10393 at the top-tier international CV/ML/AI conferences and journals, such as TPAMI, IJCV, CVPR, ECCV, ICCV, ICML, NeurIPS, ICLR, AAAI and ACM MM. He is also the leading contributor to the MMRotate , AlphaRotate and JDet open-source projects for oriented object detection, and with 8000+ stars in Github.

Xue Yang won SJTU Outstanding Doctoral Dissertation (2023), CCF Outstanding Doctoral Dissertation Award (2023), CCF-CV Academic Emerging Scholar (2022), Shanghai Outstanding Graduates (2023), Doctoral National Scholarship (2021/2022), SJTU Academic Star Nomination Award (2021), and also selected into the 10th Young Elite Scientist Sponsorship Program by CAST (2024), the Shanghai QiYuan Young Scholars Program, the World's Top 2% Scientists List (2023-2025), and the Elsevier's 2024 Most Cited Chinese Researchers.

🔥 Latest News

2026-01

One paper related to open vocabulary detection (CastDet) is accepted by IJCV. Congratulations to Yan Li. 🎉🎉🎉

2025-12

G-Rep has been selected as the winner of the Remote Sensing 2023 Best Paper Awards. Congratulations to Liping Hou. 🎉🎉🎉

2025-12

One paper related to VFM (CrossEarth) is accepted by TPAMI. Congratulations to Ziyang Gong. 🎉🎉🎉

2025-11

One survey related to VLMs evaluation is accepted by SCIENCE CHINA Information Sciences. Congrats. 🎉🎉🎉

2025-09

Two papers related to VFM (Earth-Adapter, LWGANet Oral) are accepted by AAAI 2026. Congrats. 🎉🎉🎉

2025-10

Serving as the registration chair for PRCV 2025

2025-09

Received 2024 Reviewer Certificate from IEEE TPAMI

2025-09

2025-09

Five papers related to VLM (RISE-Bench Oral), AD (Raw2Drive), 3D (GeneMAN), Object Recognition (OPMapper, InstructSAM) are accepted by NeurIPS 2025. Congrats. 🎉🎉🎉

2025-09

One paper related to VLM (AVI-MATH) is accepted by ISPRS. Congrats. 🎉🎉🎉

2025-08

I am funded by NSFC. 🎉🎉🎉

2025-08

I will serve as Area Chair for ICLR 2026

2025-08

I will serve as Senior Program Committee for AAAI 2026

2025-07

One paper related to VLM (PIIP) is accepted by TPAMI. Congrats. 🎉🎉🎉

🔥 Recent Works
Equal contribution
Corresponding author
Project Leader
IJCV
Image
【CastDet】Exploiting Unlabeled Data with Multiple Expert Teachers for Open Vocabulary Aerial Object Detection and Its Orientation Adaptation (IJCV, 2026) Citation: 3
TPAMI
Image
【CrossEarth】Geospatial Vision Foundation Model for Domain Generalizable Remote Sensing Semantic Segmentation (TPAMI, 2025) Citation: 18
arXiv
Image
【SGI-Bench】Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows (arXiv, 2025) Citation: 0
arXiv
Image
【Visionary】The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform (arXiv, 2025) Citation: 0
arXiv
Image
【SpatialRetrievalAD】Spatial Retrieval Augmented Autonomous Driving (arXiv, 2025) Citation: 1
SCIS
Image
Large Multimodal Models Evaluation A Survey (SCIS, 2025) Citation: 6
AAAI
Image
【Earth-Adapter】Bridge the Geospatial Domain Gaps with Mixture of Frequency Adaptation (AAAI, 2025) Citation: 5
AAAI
Oral
Image
【LWGANet】A Lightweight Group Attention Backbone for Remote Sensing Visual Tasks (AAAI, 2025) Citation: 25
arXiv
Image
【ProCLIP】Progressive Vision-Language Alignment via LLM-based Embedder (arXiv, 2025) Citation: 0
arXiv
Image
【MM-HELIX】Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization (arXiv, 2025) Citation: 0
arXiv
Image
【Point2RBox-v3】Self-Bootstrapping from Point Annotations via Integrated Pseudo-Label Refinement and Utilization (arXiv, 2025) Citation: 0
arXiv
Image
LLM/Agent-as-Data-Analyst A Survey (arXiv, 2025) Citation: 5
NeurIPS
Image
【InstructSAM】A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition (NeurIPS, 2025) Citation: 5
NeurIPS
Image
【OPMapper】nhancing Open-Vocabulary Semantic Segmentation with Multi-Guidance Information (NeurIPS, 2025) Citation: 0
NeurIPS
Image
【GeneMAN】Generalizable Single-Image 3D Human Reconstruction from Multi-Source Human Data (NeurIPS, 2025) Citation: 5