Automatic differentiation (autodiff) has revolutionized machine learning. Itallows to express
complex computations by composing elementary ones in creativeways and removes the …

Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models.
Recent progress in training methods has enabled successful deep SNNs on large-scale …

Many recent state-of-the-art (SOTA) optical flow models use finite-step recurrent update
operations to emulate traditional algorithms by encouraging iterative refinements toward a …

Current work in object-centric learning has been motivated by developing learning
algorithms that infer independent and symmetric entities from the perceptual input. This often …

Diffusion-based generative models are extremely effective in generating high-quality
images, with generated samples often surpassing the quality of those produced by other …

Due to the over-smoothing issue, most existing graph neural networks can only capture
limited dependencies with their inherently finite aggregation layers. To overcome this …

The ability to decompose complex natural scenes into meaningful object-centric abstractions
lies at the core of human perception and reasoning. In the recent culmination of …

Recently, implicit graph neural networks (GNNs) have been proposed to capture long-range
dependencies in underlying graphs. In this paper, we introduce and justify two weaknesses …

Cascaded computation, whereby predictions are recurrently refined over several stages, has
been a persistent theme throughout the development of landmark detection models. In this …

Reference-based line-art colorization is a challenging task in computer vision. The color,
texture, and shading are rendered based on an abstract sketch, which heavily relies on the …