AI Paper Atlas

Research map / Continual learning / Continual fine-tuning of LLMs

HiDe-PET: Continual Learning via Hierarchical Decomposition of Parameter-Efficient Tuning

Liyuan Wang, Jingyi Xie, Xingxing Zhang, Hang Su, Jun Zhu

TPAMI 2025 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation · 18 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
add within-task prediction (WTP) to the naive task-specific baseline (ablation)HiDe-LoRA · Split Cars-196 (Sup-21/1K)FAA: 45.39 -> 48.01Improved
add task-identity inference (TII) to WTP (ablation)HiDe-LoRA · Split Cars-196 (Sup-21/1K)FAA: 48.01 -> 49.62Improved
add task-adaptive prediction (TAP) to WTP (ablation)HiDe-LoRA · Split Cars-196 (Sup-21/1K)FAA: 48.01 -> 63.28Improved
add TII on top of WTP+TAP (ablation)HiDe-LoRA · Split Cars-196 (Sup-21/1K)FAA: 63.28 -> 69.65Improved
add TAP to WTP (ablation)HiDe-PreT · Split Cars-196 (Sup-21/1K)FAA: 48.23 -> 61.38Improved
add TAP to WTP (ablation)HiDe-Adapter · Split ImageNet-R (Sup-21/1K)FAA: 76.10 -> 76.98Improved
use FSA+SL instead of fix-and-tuning for task-shared parameters (ablation)HiDe-LoRA · Split Cars-196 (Sup-21/1K)FAA-U: 57.68 -> 62.89Improved
use FSA+SL instead of EMA for task-shared parameters (ablation)HiDe-Adapter · Split Cars-196 (Sup-21/1K)FAA-U: 64.46 -> 64.93Improved
use variance instead of covariance for representation recovery (ablation)HiDe-PET · Split ImageNet-R (Sup-21/1K)FAANo clear effect
replace LAE-LoRA with HiDe-LoRALAE-LoRA · Split Cars-196 (Sup-21/1K)FAA: 50.90 -> 69.65Improved
replace LAE-LoRA with HiDe-LoRALAE-LoRA · Split CUB-200 (iBOT-21K)FAA: 56.16 -> 76.10Improved
replace LAE-LoRA with HiDe-LoRALAE-LoRA · Split ImageNet-R (Sup-Weak)FAA: 57.40 -> 59.40Improved

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