6 papers
All-day Multi-scenes Lifelong Vision-and-Language Navigation with Tucker Adaptation
Xudong Wang, Gan Li, Zhiyu Liu +3
Deploying vision-and-language navigation (VLN) agents requires adaptation across diverse scenes and environments, but fine-tuning on a specific scenario often causes catastrophic f…
Lifelong Language-Conditioned Robotic Manipulation Learning
Xudong Wang, Zebin Han, Zhiyu Liu +5
Traditional language-conditioned manipulation agent sequential adaptation to new manipulation skills leads to catastrophic forgetting of old skills, limiting dynamic scene practica…
The power of small initialization in noisy low-tubal-rank tensor recovery
ZHiyu Liu, Haobo Geng, Xudong Wang +3
We study the problem of recovering a low-tubal-rank tensor from noisy linear measurements under the t-product framework. A…
Efficient Low-Tubal-Rank Tensor Estimation via Alternating Preconditioned Gradient Descent
Zhiyu Liu, Zhi Han, Yandong Tang +2
The problem of low-tubal-rank tensor estimation is a fundamental task with wide applications across high-dimensional signal processing, machine learning, and image science. Traditi…
Efficient Over-parameterized Matrix Sensing from Noisy Measurements via Alternating Preconditioned Gradient Descent
Zhiyu Liu, Zhi Han, Yandong Tang +2
We consider the noisy matrix sensing problem in the over-parameterization setting, where the estimated rank is larger than the true rank of the target matrix $X_\star…
Low-Tubal-Rank Tensor Recovery via Factorized Gradient Descent
Zhiyu Liu, Zhi Han, Yandong Tang +2
This paper considers the problem of recovering a tensor with an underlying low-tubal-rank structure from a small number of corrupted linear measurements. Traditional approaches tac…