Binqian Xu   徐斌倩 I'm a fourth-year PhD student at Nanjing University of Science and Technology, affiliated with Intelligent Media Analysis Group (IMAG), under the supervision of Prof. Xiangbo Shu. Currently, I am also a two-year visiting PhD student at A*STAR and NUS, working with Prof. Mike Z. Shou and Dr. Basura. Email: xubinq11@gmail.com Github: https://github.com/1xbq1 ORCID: https://orcid.org/0000-0003-3904-1400

Researh Interests

News

Selected Publications (*co-first author)

• 
  You Only Communicate Once: One-shot Federated Low-Rank Adaptation of MLLM
  Binqian Xu, Haiyang Mei, Zechen Bai, Jinjin Gong, Rui Yan, Guo-Sen Xie, Yazhou Yao, Basura Fernando, Xiangbo Shu
  The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS), 2025
  [pdf]|[code]
  
• 
  Tensor-aggregated LoRA in Federated Fine-tuning
  ZhiXuanLi*, Binqian Xu*, Xiangbo Shu, Jiachao Zhang, Yazhou Yao, Guo-Sen Xie, Jinhui Tang
  International Conference on Computer Vision (ICCV), 2025
  [pdf]|[code]
  
• 
  FedMLLM: Federated Fine-tuning MLLM on Multimodal Heterogeneity Data
  Binqian Xu, Xiangbo Shu, Haiyang Mei, Guo-Sen Xie, Basura Fernando, Jinhui Tang
  arXiv:2411.14717 (arXiv), 2025
  [pdf]|[code]
  
• 
  DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
  Binqian Xu, Xiangbo Shu, Haiyang Mei, Zechen Bai, Basura Fernando, Mike Zheng Shou, Jinhui Tang
  The Thirty-eighth Annual Conference on Neural Information Processing Systems (NeurIPS), 2024
  [pdf]|[code]
  
• 
  Multi-Granularity Anchor- Contrastive Representation Learning for Semi-Supervised Skeleton-Based Action Recognition
  Xiangbo Shu, Binqian Xu, Liyan Zhang, Jinhui Tang
  IEEE Transactions on Pattern Analysis and Machine Intelligence (IEEE TPAMI), 2023
  [pdf]|[code]
  
• 
  Spatiotemporal Decouple- and-Squeeze Contrastive Learning for Semi-Supervised Skeleton-based Action Recognition
  Binqian Xu, Xiangbo Shu, Jiachao Zhang, Guangzhao Dai, and Yan Song
  IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS), 2023
  [pdf]|[code]
  
• 
  X-invariant Contrastive Augmentation and Representation Learning for Semi-Supervised Skeleton-Based Action Recognition
  Binqian Xu, Xiangbo Shu, and Yan Song
  IEEE Transactions on Image Processing (IEEE TIP), 2022
  [pdf]|[code]