1 citations · 1 across the 4 of their papers we have counts for
4 papers
Detecting is Easy, Adapting is Hard: Local Expert Growth for Visual Model-Based Reinforcement Learning under Distribution Shift
Haiyang Zhao
Visual model-based reinforcement learning (MBRL) agents can perform well on the training distribution, but often break down once the test environment shifts. In visual MBRL, recogn…
One-Shot Pruning for Fast-adapting Pre-trained Models on Devices
Haiyan Zhao, Guodong Long
Large-scale pre-trained models have been remarkably successful in resolving downstream tasks. Nonetheless, deploying these models on low-capability devices still requires an effect…
Does Continual Learning Equally Forget All Parameters?
Haiyan Zhao, Tianyi Zhou, Guodong Long +2
Distribution shift (e.g., task or domain shift) in continual learning (CL) usually results in catastrophic forgetting of neural networks. Although it can be alleviated by repeatedl…
Voting from Nearest Tasks: Meta-Vote Pruning of Pre-trained Models for Downstream Tasks
Haiyan Zhao, Tianyi Zhou, Guodong Long +2
As a few large-scale pre-trained models become the major choices of various applications, new challenges arise for model pruning, e.g., can we avoid pruning the same model from scr…