AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

NAOMI: Non-Autoregressive Multiresolution Sequence Imputation

Yukai Liu, Rose Yu, Stephan Zheng, Eric Zhan, Yisong Yue

NeurIPS 2019 · Probabilistic and scientific modeling › Molecules and proteins · approach: Flow matching generative modeling · 16 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
decode non-autoregressively at multiple resolutions instead of single-resolution autoregressive decoding (ablation)NAOMI vs SingleRes · PEMS-SF trafficL2 loss (1e-4): 4.51 -> 3.54Improved
decode non-autoregressively at multiple resolutions instead of single-resolution autoregressive decoding (ablation)NAOMI vs SingleRes · BilliardsL2 loss (1e-2): 0.233 -> 0.067Improved
decode non-autoregressively at multiple resolutions instead of single-resolution autoregressive decoding (ablation)NAOMI vs SingleRes · Billiardsstep change (1e-3): 9.290 -> 7.239Improved
decode non-autoregressively at multiple resolutions instead of single-resolution autoregressive decoding (ablation)NAOMI vs SingleRes · BasketballStep Change (1e-3): 4.811 -> 2.565Improved
decode non-autoregressively at multiple resolutions instead of single-resolution autoregressive decoding (ablation)NAOMI vs SingleRes · BasketballPlayer Distance: 0.417 -> 0.423No clear effect
use multiresolution NAOMI instead of linear interpolationNAOMI · Billiardsstep change (1e-3): 0.961 -> 7.239Hurt
use NAOMI instead of KNNNAOMI · BasketballOOB Rate (1e-3): 0.128 -> 1.733Hurt
increase proportion of missing values (ablation)NAOMI and SingleRes · Billiardsimputation qualityHurt
apply per-step discriminator with adversarial imitation (MaskGAN) vs whole-sequence discriminator (GRUI)imputation baselines · PEMS-SF trafficL2 loss (1e-4): 15.24 -> 6.02Improved

Later papers that compared with this method

1 later accepted paper reports NAOMI as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy