深度学习中的不确定性(Uncertainty)

使用贝叶斯深度学习建模深度学习中的不确定性.

主动学习(Active Learning)

Active Learning.

SIoU Loss: More Powerful Learning for Bounding Box Regression

SIoU Loss:学习更强大的边界框回归.

Training language models to follow instructions with human feedback

使用人类反馈训练语言模型遵循指令.

Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks

超自然指令:通过声明式指令在 1600 多个 NLP 任务上进行泛化.

Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?

重新思考演示的作用:什么导致上下文学习有效?