Publications

Selected Publications

Please refer to the Google Scholar profile for more up-to-date papers.

	Token Expand-Merge: Training-Free Token Compression for Vision-Language-Action Models Yifan Ye, Jiaqi Ma, Jun Cen, Zhihe Lu^† † Corresponding author RAL, 2026 A training-free token compression framework that accelerates VLA inference with token expanding and merging.
	Self-evolved Imitation Learning in Simulated World Yifan Ye, Jun Cen, Jing Chen^†, Zhihe Lu^† † Corresponding author RAL, 2026 A framework that progressively improves a few-shot model through simulator interactions.
	Controllable Federated Prompt Learning at Test Time Rui Zhu, Liang Bai, Yanming Guo, Yirun Ruan, Tianyuan Yu^†, Zhihe Lu^† † Corresponding author CVPR, 2026 A very early attempt to conduct test-time prompt learning in federated domain.
	COLA: Context-aware Language-driven Test-time Adaptation Aiming Zhang, Tianyuan Yu, Liang Bai, Jun Tang, Yanming Guo, Yirun Ruan, Yun Zhou, Zhihe Lu^† † Corresponding author TIP, 2025 code A method that leverages domain information and language guidance to adapt VLMs at test time.
	Task-to-Instance Prompt Learning for Vision-Language Models at Test Time Zhihe Lu^, Jiawang Bai^, Xin Li, Zeyu Xiao, Xinchao Wang * Equal Contribution TIP, 2025 code A two-stage pipeline to alleivate the difficulty of VLMs adaptation at test time.
	Beyond Sole Strength: Customized Ensembles for Generalized Vision-Language Models Zhihe Lu, Jiawang Bai, Xin Li, Zeyu Xiao, Xinchao Wang ICML, 2024 code The first investigation of ensemble learning for VLMs.
	GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph Xin Li^, Dongze Lian^, Zhihe Lu^, Jiawang Bai, Zhibo Chen, Xinchao Wang Equal Contribution NeurIPS, 2023 code Introduce knowledge graph for tuning vision and language models.
	Frequency-enhanced Data Augmentation for Vision-and-Language Navigation Keji He, Chenyang Si, Zhihe Lu, Yan Huang, Liang Wang, Xinchao Wang NeurIPS, 2023 code A work to explore the significance of high-frequency information for enhanced Vision-and-Language Navigation.
	Uncertainty-aware Source-free Domain Adaptive Semantic Segmentation Zhihe Lu, Da Li, Yi-Zhe Song, Tao Xiang, Timothy M. Hospedales TIP, 2023 An uncertainty-aware solution for SFDASS.
	Prediction Calibration for Generalized Few-shot Semantic Segmentation Zhihe Lu, Sen He, Da Li, Yi-Zhe Song, Tao Xiang TIP, 2023 Investigating the feature-prediction covariance based Transformer for calibrating the biases in GFSS.
	Task Residual for Tuning Vision-Language Models Tao Yu^, Zhihe Lu^, Xin Jin, Zhibo Chen, Xinchao Wang * Equal Contribution CVPR, 2023 code A simple yet effective tuning method for vision and language models.
	Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformer Zhihe Lu, Sen He, Xiatian Zhu, Li Zhang, Yi-Zhe Song, Tao Xiang ICCV, 2021 code A novel training pipeline for few-shot segmentation with classifier weight transformer.
	Stochastic Classifiers for Unsupervised Domain Adaptation Zhihe Lu, Yongxin Yang, Xiatian Zhu, Cong Liu, Yi-Zhe Song, Tao Xiang CVPR, 2020 code A novel way to use infinite number of classifiers without extra parameters to identify misaligned regions.
	Conditional Expression Synthesis with Face Parsing Transformation Zhihe Lu, Tanhao Hu, Lingxiao Song, Zhaoxiang Zhang, Ran He ACM MM, 2018 A Couple-Agent Face Parsing based Generative Adversarial Network (CAFP-GAN) that unites the knowledge of facial semantic regions and controllable expression signals.
	Geometry Guided Adversarial Facial Expression Synthesis Lingxiao Song, Zhihe Lu, Ran He, Zhenan Sun, Tieniu Tan ACM MM, 2018 A Geometry-Guided Generative Adversarial Network (G2-GAN) was proposed for photorealistic and identity-preserving facial expression synthesis.
	Recent Progress of Face Image Synthesis Zhihe Lu, Zhihang Li, Jie Cao, Ran He, Zhenan Sun ACPR, 2017 A very early survey for face image synthesis.