AI Paper Atlas

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

MAGIC: Meta-Ability Guided Interactive Chain-of-Distillation for Effective-and-Efficient Vision-and-Language Navigation

Liuyi Wang, Zongtao He, Mengjiao Shen, Jingwei Yang, Chengju Liu, Qijun Chen

TPAMI 2026 · Label-efficient and robust learning › Knowledge distillation · approach: Rethinking distillation objectives

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 meta-ability knowledge distillation (MAKD) (ablation)MAGIC-B · R2R val-unseenSR: 74.88 -> 76.33Improved
add meta-ability knowledge distillation (MAKD) (ablation)MAGIC-B · R2R val-unseenSPL: 64.82 -> 67.86Improved
add global topological cross-modal location knowledge transfer (ablation)MAGIC-B MAKD · R2R val-unseenSR: 73.95 -> 76.33Improved
add behavior decision-making knowledge transfer (ablation)MAGIC-B MAKD · R2R val-unseenOSR: 84.89 -> 83.61Hurt
add text knowledge transfer (ablation)MAGIC-B MAKD · R2R val-unseenSR: 75.78 -> 76.33Improved
add transfer of hidden features to attention and logits KD (ablation)MAGIC-B MAKD · R2R val-unseenSR: SR drops 1.9%Improved
use randomization weighting (MKRW) instead of EqualAdd, LearnedWeights, GradAdjust (ablation)MAKD losses · R2R val-unseenSR and SPLImproved
add teacher determination weighting (beta=0.7) instead of beta=0 (ablation)MKTD · R2R val-unseenSPL: SPL drops 1.6% at beta=0Improved
increase MKTD attenuation beta to 0.9 (ablation)MKTD · R2R val-unseenSPL: SPL reduces 4.5%Hurt
add interactive co-training (ICoD) with student feedback (ablation)MAGIC-S · R2R val-unseenSR: 73.44 -> 76.03Improved
add interactive co-training (ICoD) (ablation)MAGIC-L teacher · R2R val-unseenSR: 77.82 -> 78.76Improved
continue training teacher without student feedback (ablation)teacher model · R2RgeneralizationHurt

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