Paper Detail

Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning

Zhiming Xu, Huiyu Yi, Zhen-Hao Xie, Baile Xu, Furao Shen, Jian Zhao, Suorong Yang

arxiv Score 13.0

Published 2026-08-17 · First seen 2026-08-18

Research Track A

Abstract

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.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{xu2026task,
  title = {Task-Anchored Representation Shaping for Pre-Trained Model-Based Continual Learning},
  author = {Zhiming Xu and Huiyu Yi and Zhen-Hao Xie and Baile Xu and Furao Shen and Jian Zhao and Suorong Yang},
  year = {2026},
  abstract = {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 Laten},
  url = {https://arxiv.org/abs/2608.16345},
  keywords = {cs.LG},
  eprint = {2608.16345},
  archiveprefix = {arXiv},
}

Metadata

{}