Metraipolis › archive › dc_f3eea0867505

Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning — arXiv:2608.16345

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16345
License (as archived)
CC0-1.0
Archived
2026-10-18T19:41:36.195Z
SHA-256 of the archived text
5f138bc2414e733167aff1e708587bf015b49f7a907ed008911f1b0b95bcf445
Stable URL of this page
https://metraipolis.com/documento/dc_f3eea0867505

How to cite

Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning — arXiv:2608.16345 — arXiv (en), https://arxiv.org/abs/2608.16345 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f3eea0867505 (Metraipolis archive dc_f3eea0867505, sha256 5f138bc2414e733167aff1e708587bf015b49f7a907ed008911f1b0b95bcf445)
BibTeX
@misc{dcf3eea0867505,
  title = {Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning — arXiv:2608.16345},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16345},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f3eea0867505; sha256 5f138bc2414e733167aff1e708587bf015b49f7a907ed008911f1b0b95bcf445},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16345. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Pre-trained models (PTMs) provide a strong foundation for continual learning by offering stable representations that facilitate lightweight adaptation to new tasks. However, adapting well to each task does not ensure reliable inference over all learned tasks. Since task boundaries are often artificial and semantically entangled, an input from an unknown task can remain ambiguous even with strong PTM features, making cross-task prediction a key bottleneck. We propose Task-Anchored Inference Latent Shaping (TAILS), a lightweight post-PTM module that can be integrated into diverse continual learners and optimized through a decoupled step. TAILS uses fixed task anchors as persistent references to accumulated knowledge. It interprets each sample's feature representation relative to these references, then composes relevant evidence across tasks into latent recall. Rather than selecting a task-specific path or adjusting classifier outputs, TAILS uses latent recall to directly correct the feature representation before prediction. It therefore resolves cross-task ambiguity at the representation level, while leaving the original PTM, method-specific modules, and classifier unchanged. Extensive experiments across multiple PTM-based continual learning paradigms show that TAILS can improve classification and task-inference performance with modest parameter overhead and negligible inference cost.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.16345 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T19:02:44.168Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).