Lixian Chen

Lixian Chen

Undergraduate focusing on Multimodal Learning, Vision-Language Models.

Lixian Chen

Hi! I am Lixian Chen, an undergraduate student at Guangdong University of Technology.

My research focuses on multimodal learning, vision-language models.
Recently, I have been working on topics such as test-time adaptation and geometric learning in hyperbolic spaces.

News

  • [2026.05] 🏆 🏆 My paper was accepted by Neural Networks !
  • [2026.05] 🎉 🎉 My paper as a co-first author was accepted by SIGKDD 2026.
  • [2026.04] 🏆 🏆 My paper was accepted by ICIC 2026 as an oral presentation!

Publications

Over-squashing as Transport Congestion: A Sandpile Dynamics Perspective

KDD 2026 (CCF-A)

Yang Shi*, Lixian Chen*, et al.

Majorization Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift

Under Review at ACM MM 2026 (CCF-A)

Lixian Chen, Mingxuan Huang, Yanhui Chen, Junyi Lin, Yang Shi

When Task Performance Deceives: Task-Geometry Decoupling in Learnable-Curvature Hyperbolic GNNs

Neural Networks (CCF-B)

Lixian Chen, Jingchao Wang, Zhaorong Dai, Hanqian Liu, Danxiang Ai, Yang Shi

Hyperbolic Vision Graph Neural Networks for Image Classification

ICIC 2026 (Oral, CCF-C)

Lixian Chen, Heng Yin, Mingxuan Huang, Weizhe Lan, Hanqian Liu, Link He, Honting Tang