AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

The Tutor-Pupil Augmentation: Enhancing Learning and Interpretability via Input Corrections

Darya Biparva, Maarten Schoukens, Donatello Materassi

ICLR 2026 · Label-efficient and robust learning › Recognition and long-tail · approach: Data augmentation and generalization bias

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 a Tutor network that learns minimal input corrections to a decision-tree Pupilshallow decision tree · Toy 2D classification (test)accuracy: 0.8588 -> 0.9705Improved
add a Tutor network to a decision-tree Pupilshallow decision tree · Toy 2D classification (test)precision: 0.8413 -> 0.9512Improved
add a Tutor network to a decision-tree Pupilshallow decision tree · Toy 2D classification (test)loss per sample: 0.4446 -> 1.0350Hurt
add a latent-space VAE Tutor to a logistic regression Pupillogistic regression · MNIST testaccuracy: 91 -> 98.5Improved
add a Tutor learning volume and temperature corrections to the ideal gas law Pupilideal gas law · 2D hard-disk gas simulationpressure predictionImproved

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