Sikai Bai

Most-cited papers

1. DiPrompT: Disentangled Prompt Tuning for Multiple Latent Domain Generalization in Federated Learning

   Sikai Bai, Jiewei Zhang, Song Guo, Shuaicheng Li +4 more

   2024Computer Vision and Pattern Recognition43 citations Open access

   Semantic Scholar

   Save

2. DiEP: Adaptive Mixture-of-Experts Compression through Differentiable Expert Pruning

   Sikai Bai, Haoxi Li, Jie M. Zhang, Zi-Cong Hong +1 more

   2025Neural Information Processing Systems33 citations

   Semantic Scholar

   Save

3. Combating Data Imbalances in Federated Semi-supervised Learning with Dual Regulators

   Sikai Bai, Shuaicheng Li, Weiming Zhuang, J. Zhang +6 more

   2023AAAI Conference on Artificial Intelligence23 citations Open access

   Semantic Scholar

   Save

4. DRPT: Disentangled and Recurrent Prompt Tuning for Compositional Zero-Shot Learning

   Xiao-Cheng Lu, Zi-Ming Liu, Song Guo, Jing-Cai Guo +3 more

   2023arXiv.org21 citations Open access

   Semantic Scholar

   Save

5. Causally Motivated Sycophancy Mitigation for Large Language Models

   Haoxi Li, Xueyang Tang, Jie M. Zhang, Song Guo +3 more

   2025International Conference on Learning Representations17 citations

   Semantic Scholar

   Save

6. CoRE: Enhancing Metacognition with Label-free Self-evaluation in LRMs

   Haoxi Li, Sikai Bai, Jie M. Zhang, Song Guo

   2025arXiv.org7 citations

   Semantic Scholar

   Save

7. MFI: Multi-range Feature Interchange for Video Action Recognition

   Sikai Bai, Qi Wang, Xue-Long Li

   2021International Conference on Pattern Recognition5 citations

   Semantic Scholar

   Save

8. TTVS: Boosting Self-Exploring Reinforcement Learning via Test-time Variational Synthesis

   Sikai Bai, Haoxi Li, Jie M. Zhang, Yong-Jiang Liu +1 more

   2026Annual Meeting of the Association for Computational Linguistics2 citations

   Semantic Scholar

   Save

9. Unsupervised Domain Adaptive Learning via Synthetic Data for Person Re-identification

   Qi Wang, Sikai Bai, Junyuan Gao, Yuan Yuan +1 more

   2021arXiv.org2 citations

   Semantic Scholar

   Save

10. What You Think is What You See: Driving Exploration in VLM Agents via Visual-Linguistic Curiosity

    Haoxi Li, Qi Hou, Jianfei Ma, Jinxiang Lai +5 more

    2026arXiv.org1 citations

    Semantic Scholar

    Save

11. Multi-Domain Synchronous Refinement Network for Unsupervised Cross-Domain Person Re-Identification

    Sikai Bai, Junyu Gao, Qi Wang, Xue-Long Li

    2021IEEE International Conference on Multimedia and Expo1 citations

    Semantic Scholar

    Save

12. Edge-Efficient Compositional Recognition via Disentangled Prompt Tuning of Frozen Vision-Language Models

    Xiao-Cheng Lu, Chuan He, Zi-Ming Liu, Fu-Shuo Huo +3 more

    0 citations

    Semantic Scholar

    Save