AI Paper Atlas

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

PACT: Phase-Like Transition Constraints in Adapter-Based Continual Learning of Vision-Language Models

Xuan Wang, Guiguang Ding, Jungong Han

CVPR 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Mixture-of-experts for multimodal continual tuning

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
replace per-task LoRA with MLP-structured adapters using only SAI (1)(2) (no gate) (ablation)PACT · MTIL Order-ILast accuracy: 79.54 -> 9.83Hurt
add convex gating (SAI 4) to the adapter (ablation)PACT · MTIL Order-ILast accuracy: 9.83 -> 85.60Improved
add all components (SAI cloning, Lmarg, Lstab, post-convergence) on top of gated adapter (ablation)PACT · MTIL Order-ILast accuracy: 85.60 -> 90.54Improved
PACT vs best prior baseline on MTILCLIP ViT-B/16 · MTIL Order-ILast accuracy: +2.94Improved
use PACT in few-shot MTIL 16-shotCLIP ViT-B/16 · FS-MTIL 16-shotLast accuracy: 77.7 -> 84.4Improved
use PACT in CIL on CIFAR100 (10 steps)CLIP ViT-B/16 · CIFAR100 CILLast accuracy: 79.33 -> 80.57Improved

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