Papers/2611.25126
🧪 Test?View on arXiv

TALD: Transferability-Aware Logit Disentanglement for Cross-Modal Knowledge Distillation

Not provided in the abstract

cross-modalknowledge distillationlogit disentanglementtransfer learning
2611.25126
Builder Relevance
80%
2d ago

Abstract

TALD proposes a two-stage framework for improving cross-modal knowledge distillation by addressing negative transfer through logit disentanglement.

Reality Card

Core Claim

TALD achieves the largest mean accuracy gain and highest positive-transfer frequency across five benchmarks compared to existing methods.

Method / Result

TALD improves over training without distillation in 84% of evaluations.

Limitations

The paper does not specify limitations or reproducibility concerns.

Paper to code

Verified implementation resources so builders can test the paper’s claims instead of stopping at the abstract.

No verified implementation link has been attached yet. AIBuzzHub will keep this panel separate from unverified search results.
← Back to all papers