Task-Robust Pre-Training for Worst-Case Downstream Adaptation Jianghui Wang, Y ang Chen
–Neural Information Processing Systems
Pre-training has achieved remarkable success when transferred to downstream tasks. In machine learning, we care about not only the good performance of a model but also its behavior under reasonable shifts of condition.
Neural Information Processing Systems
Feb-8-2026, 16:25:36 GMT
- Country:
- North America > United States
- Washington > King County > Seattle (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.04)
- Asia
- China (0.04)
- Middle East > Jordan (0.04)
- North America > United States
- Genre:
- Research Report > New Finding (0.46)
- Technology: