AI Paper Atlas

Research map / Label-efficient and robust learning / Knowledge distillation

On the Distillation of Stories for Transferring Narrative Arcs in Collections of Independent Media

Dylan R. Ashley, Vincent Herrmann, Zachary Friggstad, Jürgen Schmidhuber

TPAMI 2024 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives · 2 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
increase narrative essence dimension from 1 to 16 (ablation)Narrative essence · FMA validationmutual information (bits): 1.924 -> 1.975No clear effect
use learned narrative essence instead of valence, energy or tempoStory templates · FMA albumsmutual information with orderImproved
use learned templates instead of shuffled-essence baselineStory templates k=4 · FMA test setstring edit score: significant at p < 0.05Improved
increase number of templates from 3 to 4 (ablation)Template extraction · FMA albumstemplate set qualityImproved

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