About me

Academic visit I am currently seeking a 3–6 month academic visiting opportunity, with funding fully covered by my PhD programme in Italy.

Hi, I am Zanxi. I am a second-year PhD candidate at the University of Verona, supervised by Prof. Marco Cristani and Dr. Yiming Wang.

My research focuses on multimodal representation learning, particularly the geometry, alignment, and biases of vision-language representations. I am particularly interested in extending this work toward embodied intelligence, with a focus on robust perception, multimodal reasoning, and transferable representations for interactive agents.

Previously, I earned my Master's degree from the National University of Defense Technology and my Bachelor's degree, ranked 1st of 70, from North China University of Technology.

Multimodal learning Vision–language alignment Embodied intelligence

How I work I bring a positive and hard-working attitude to research and genuinely value every opportunity I receive. I have extensive experience collaborating in research teams and enjoy sharing ideas, taking responsibility, and growing together with others.

My hobbies I enjoy drawing and playing tennis .

News

  • Sep, 2026 I have just submitted my first theory-oriented work to ICLR 2027. Fingers crossed!
  • Sep, 2026 Our follow-up to StructXLIP, Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment, has been accepted to NeurIPS 2026. More details are coming soon.
  • Aug, 2026 I am delighted to be co-organizing the Human-AI Co-Creation Workshop at ECCV 2026.
  • Jun, 2026 StructXLIP received the CVPR Compute Transparency Champion award, recognizing our high-quality anonymized Weights & Biases logs and complete compute reporting.
  • May, 2026 One paper has been accepted to ICIP 2026.
  • Feb 21, 2026 Our work StructXLIP has been accepted to CVPR 2026. Thanks to Yiming and Marco.
  • Feb, 2026 One paper accepted at ICLR 2026.
  • Jun, 2025 One paper accepted at ICCV 2025.
  • Jun, 2025 My final master's research, "Few-shot event-based action recognition", has been accepted by Neural Networks. This work marks a nice conclusion to my M.Sc. journey.

Selected Publications

CVPR2026 StructXLIP method overview
StructXLIP: Enhancing Vision-Language Models with Multimodal Structural Cues
Z. Ruan, Q. Kong, S. GAO, Y. Wang, M. Cristani
CVPR 2026 — The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2026
CVPR
NeurIPS2026 Mitigating Saliency Collapse
Mitigating Saliency Collapse: Robust Saliency-Aware Long-Text Image-Text Alignment
Q. Kong, Z. Ruan*, M. Cristani, Y. Wang
* Corresponding author
NeurIPS 2026 — In Proceedings of Neural Information Processing Systems (NeurIPS), 2026
NeurIPS Coming Soon
ICIP2026 SAM3 pathology segmentation results
Is SAM3 ready for pathology segmentation?
Q. Kong, S. Sharifi, Y. Wang, M. Cristani, Z. Ruan*
* Corresponding author
ICIP 2026 — IEEE International Conference on Image Processing
ICIP
PDF
ICLR2026 Decost
Learning to Solve Orienteering Problem with Time Windows and Variable Profits
S. Gao, Z. Ruan*, P. Floor, M. Roveri, L. Palopoli, D. Fontanelli
* Corresponding author
ICLR 2026 — The Fourteenth International Conference on Learning Representations
ICLR
ICCV2025 · Oral LOTS of Fashion
LOTS of Fashion! Multi-conditioning for Image Generation via Sketch-Text Pairing
F. Girella, D. Talon, Z. Liu, Z. Ruan, Y. Wang, M. Cristani
ICCV 2025 (Oral) — Proceedings of The IEEE/CVF International Conference on Computer Vision
ICCV
Neural Networks2025 Few-shot Event-based Action Recognition
Few-shot Event-based Action Recognition
Z. Ruan, N. Pu, J. Chen, S. Gao, Y. Guo, Q. Kong, Y. Xie, Y. Wei
Neural Networks, 191, 107750, 2025
JCR Q1
ACM MM2024 Dual-branch Fusion
Dual-branch Fusion with Style Modulation for Cross-domain Few-shot Semantic Segmentation
Q. Kong, J. Chen, J. Jiang, Z. Ruan, L. Kang
ACM Multimedia 2024 — Proceedings of the 32nd ACM International Conference on Multimedia
ACM MM
C&IS2024 Hybrid Attentive Prototypical Network
Hybrid Attentive Prototypical Network for Few-shot Action Recognition
Z. Ruan, Y. Wei, Y. Guo, Y. Xie
Complex & Intelligent Systems, 10 (6), 8249–8272, 2024
JCR Q1

Community Service

Workshop Organization

Co-organizer of the Human-AI Co-Creation Workshop at ECCV 2026.

Peer Review

Reviewer for ICCV, CVPR, Neurips, ACM Multimedia (ACM MM), ICLR, and IEEE Transactions on Multimedia (TMM).

Reviewer Recognition

  • 2026 Top ReviewerNeurIPS
  • 2025 Outstanding ReviewerACM Multimedia (ACM MM)