This paper surveys the recent attempts at leveraging machine learning to solve constrained
optimization problems. It focuses on surveying the work on integrating combinatorial solvers …

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 …

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 …

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 …

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 …