featured

Accelerating Transformer Inference for Translation via Parallel Decoding
Autoregressive decoding limits the efficiency of transformers for Machine Translation (MT). The community proposed specific network …
PDF Cite arXiv GitHub
Accelerating Transformer Inference for Translation via Parallel Decoding
Latent Autoregressive Source Separation
Autoregressive models have achieved impressive results over a wide range of domains in terms of generation quality and downstream task …
Cite arXiv GitHub
Latent Autoregressive Source Separation
Relative representations enable zero-shot latent space communication
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations. …
PDF Cite URL GitHub Slides ICLR 2023 notable top 5%
Relative representations enable zero-shot latent space communication
Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning
Predicting interactions between proteins and other biomolecules solely based on structure remains a challenge in biology. A high-level …
Cite
Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning
LIMP: Learning Latent Shape Representations with Metric Preservation Priors
In this paper, we advocate the adoption of metric preservation as a powerful prior for learning latent representations of deformable 3D …
Cite arXiv GitHub
LIMP: Learning Latent Shape Representations with Metric Preservation Priors
Isospectralization, or how to hear shape, style, and correspondence
The question whether one can recover the shape of a geometric object from its Laplacian spectrum (‘hear the shape of the …
Cite DOI PDF GitHub
Isospectralization, or how to hear shape, style, and correspondence
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence
We introduce a new framework for learning dense correspondence between deformable 3D shapes. Existing learning based approaches model …
Cite
Deep Functional Maps: Structured Prediction for Dense Shape Correspondence