AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Incremental Transformer Neural Processes

Philip Mortimer, Cristiana Diaconu, Tommy Rochussen, Bruno Kacper Mlodozeniec, Richard E. Turner

ICML 2026 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Bayesian view of meta-learning · 0 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
add dense autoregressive sequence training (incTNP-Seq) to incTNP (ablation)incTNP · Protein (factorised)test log-likelihood delta vs TNP-D: -0.028 -> +0.036Improved
add dense autoregressive sequence training to incTNP (ablation)incTNP · Temperature (Forecast) (factorised)test log-likelihood delta vs TNP-D: +0.030 -> +0.690Improved
add dense autoregressive sequence training to incTNP (ablation)incTNP · 1D GP (factorised)test log-likelihood delta vs TNP-D: -0.013 -> -0.002Improved
add dense autoregressive sequence training to incTNP (ablation)incTNP · Elevators (factorised)test log-likelihood delta vs TNP-D: -0.024 -> -0.009Improved
replace TNP-D with causally masked incTNP-Seq in AR deploymentTNP-D · Temperature (Interp) (AR)inference cost ratio: 3.57x -> 1.00xImproved
replace TNP-D with incTNP-Seq in AR deploymentTNP-D · Temperature (Forecast) (AR)test log-likelihood: -1.749 -> +0.061 deltaImproved
use incTNP-Seq instead of CNPCNP · 1D GP (factorised)test log-likelihood delta vs TNP-D: -0.230 -> -0.002Improved
use incTNP-Seq instead of LBANPLBANP · Tabular (Synthetic) (factorised)test log-likelihood delta vs TNP-D: -0.058 -> +0.007Improved
give TNP-D and incTNP equal compute budget to incTNP-Seq (ablation)TNP-D and incTNP · 1D GP and Tabular hyperparameter sweeppeak test log-likelihoodNo clear effect
add dense autoregressive training for hyperparameter robustness (ablation)incTNP · 1D GP and Tabular sweepvariance across configurationsImproved
add causal masking to TNP-D (incTNP) for implicit BayesiannessTNP-D · 1D GPKL gapNo clear effect
use incTNP-Seq instead of WISKI streaming GPWISKI · 1D GP streamingKL gap and performanceImproved

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