Siyuan Li

Shanghai Jiao Tong University — China

Computer Science · Physical Sciences

17h-index1.1kcitations79works5.52yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Advanced Vision and Imaging(14), Video Surveillance and Tracking Methods(12), Human Pose and Action Recognition(10), Advanced Graph Neural Networks(7), Domain Adaptation and Few-Shot Learning(7)

Publications79 total

Artifact Removal Method for Electrical Impedance Tomography Utilizing a Multi-Scale Attention Mechanism
IEEE Access·2026Open Access
UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025· 7 citedOpen Access
FGeneBERT: function-driven pre-trained gene language model for metagenomics
Briefings in Bioinformatics·2025Open Access
ResearchPulse: Building Method-Experiment Chains through Multi-Document Scientific Inference
2025Open Access
Semantic-Condition Tuning: Fusing Graph Context with Large Language Models for Knowledge Graph Completion
arXiv (Cornell University)·2025Open Access
ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos
arXiv (Cornell University)·2025Open Access
SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
2025
Multi-View 3D Point Tracking
arXiv (Cornell University)·2025Open Access
SketchAgent: Generating Structured Diagrams from Hand-Drawn Sketches
arXiv (Cornell University)·2025Open Access
3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection
arXiv (Cornell University)·2025Open Access
TrinityDNA: A Bio-Inspired Foundational Model for Efficient Long-Sequence DNA Modeling
arXiv (Cornell University)·2025Open Access
Pseudo-panchromatic image color difference demosaicking for a 41-band snapshot imaging system using a dual-MSFA
Optics Letters·2025
UniK3D: Universal Camera Monocular 3D Estimation
2025· 6 cited
From Words to Structured Visuals: A Benchmark and Framework for Text-to-Diagram Generation and Editing
2025· 3 cited
One2Any: One-Reference 6D Pose Estimation for Any Object
2025· 1 cited
N-terminal basic residues of HOXD9 homeodomain drives its target-site searching along DNA
International Journal of Biological Macromolecules·2025
One2Any: One-Reference 6D Pose Estimation for Any Object
arXiv (Cornell University)·2025Open Access
USTEP: Spatio-Temporal Predictive Learning Under a Unified View
IEEE Transactions on Pattern Analysis and Machine Intelligence·2025
New Findings of Efficient Low-TemperatureComplex Cellulose-Degrading Bacteria:a Comprehensive Study
Polish Journal of Environmental Studies·2025· 7 citedOpen Access
UniK3D: Universal Camera Monocular 3D Estimation
arXiv (Cornell University)·2025Open Access
page 1 of 4Next →

Frequent Co-authors

Stan Z. Li(21), Zhangyang Gao(10), Lirong Wu(9), Zelin Zang(8), Cheng Tan(6), Jun Xia(6), Mattia Segù(6), Fisher Yu(6), Yongjie Xu(5), Luigi Piccinelli(5), Luc Van Gool(5), Zicheng Liu(5), Yung-Hsu Yang(4), Christos Sakaridis(4), Di Wu(4), Qianhao Min(3), Xueqin Chen(3), Jun‐Jie Zhu(3), Martin Danelljan(3), Haitao Lin(3)