Xiangli Nie

2 accepted papers

2025

FAGR: Feature-Action Generative Replay for Robot Lifelong Imitation Learning

RA-L 2025

Conventional imitation learning (IL) struggles with scalability and catastrophic forgetting in sequential task learning, prompting the need for Lifelong Imitation Learning (LIL) to enable sustainable knowledge accumulation. However, existing LIL approaches, which largely depend on replaying demonstr

Cited by 0 Source ↗Scholar ↗

2025

FRET: Feature Redundancy Elimination for Test Time Adaptation

Linjing You, Jiabao Lu, Xiayuan Huang, Xiangli Nie

ICCV 2025poster

Test-Time Adaptation (TTA) aims to enhance the generalization of deep learning models when faced with test data that exhibits distribution shifts from the training data. In this context, only a pre-trained model and unlabeled test data are available, making it particularly relevant for privacy-sensi…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗