A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
Cycle3D proposes a unified 3D generation framework that enhances diversity and texture consistency through a generation-reconstruction cycle during the denoising process.
Unknown
Proposes an efficient sparse attention method for diffusion language models that skips sparse attention in early denoising steps and reuses sparse patterns later.
Graves, Alex
Proposes an LSTM-based recurrent neural network for denoising and predicting GNSS time series, achieving 50% noise reduction and 1.1 mm MSE prediction error.
Riccardo Miotto, Li Li, Brian Kidd, et al.
Unsupervised deep feature learning with stacked denoising autoencoders on EHRs of ~700k patients yields a general-purpose patient representation that significantly improves predictive modeling for 78 diseases.
Unknown
mBART pre-trains a multilingual sequence-to-sequence denoising auto-encoder on large-scale monolingual corpora using the BART objective, significantly improving machine translation.
Ruoqian Lin, Rui Zhang, Chunyang Wang, et al.
This paper presents a deep-learning library and models for robust atom segmentation, localization, denoising, and deblurring in atomic-resolution STEM images, outperforming conventional methods.
Bing Xu, Junfei Zhang, Rui Wang, et al.
This paper uses generative adversarial networks to denoise Monte Carlo renderings, producing more realistic high-frequency details and global illumination.
Chitwan Saharia, Jonathan Ho, William Chan, et al.
SR3 adapts denoising diffusion probabilistic models to image super-resolution via iterative refinement, achieving near-perfect fool rates on face super-resolution.
Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, et al.
A comprehensive survey of denoising diffusion models in computer vision, covering theoretical frameworks, relations to other generative models, and future research directions.