C Deng, X Ji, C Rainey, J Zhang, W Lu - Iscience, 2020 - cell.com
Machine learning has been heavily researched and widely used in many disciplines. However, achieving high accuracy requires a large amount of data that is sometimes …
At present, the mechanisms of in-context learning in Transformers are not well understood and remain mostly an intuition. In this paper, we suggest that training Transformers on auto …
J Xie, F Long, J Lv, Q Wang… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
Few-shot classification is a challenging problem as only very few training examples are given for each new task. One of the effective research lines to address this challenge …
P Kidger - arXiv preprint arXiv:2202.02435, 2022 - arxiv.org
The conjoining of dynamical systems and deep learning has become a topic of great interest. In particular, neural differential equations (NDEs) demonstrate that neural networks …
We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly …
Z Teed, J Deng - Computer Vision–ECCV 2020: 16th European …, 2020 - Springer
Abstract We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …
We present Theseus, an efficient application-agnostic open source library for differentiable nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …
In this paper, we address the few-shot classification task from a new perspective of optimal matching between image regions. We adopt the Earth Mover's Distance (EMD) as a metric to …
Automatic differentiation (autodiff) has revolutionized machine learning. Itallows to express complex computations by composing elementary ones in creativeways and removes the …