AI Paper Atlas

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

Towards Dynamic Modality Alignment in Multimodal Continual Learning

Jiayao Tan, Fan Lyu, Tianle Liu, Fuyuan Hu, Wei Feng

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
add graph regularization (all three losses) (ablation)DAGR · MTILAvg. accuracy: 71.2 -> 79.4Improved
add graph regularization (all three losses) (ablation)DAGR · MTILLast accuracy: 79.5 -> 87.1Improved
add inter-layer path consistency loss alone (ablation)DAGR · MTILAvg. accuracy: 71.2 -> 75.4Improved
add multi-hop edge consistency loss alone (ablation)DAGR · MTILAvg. accuracy: 71.2 -> 74.1Improved
add edge consistency loss alone (ablation)DAGR · MTILAvg. accuracy: 71.2 -> 73.0Improved
add edge loss to multi-hop plus path losses (ablation)DAGR · MTILAvg. accuracy: 77.6 -> 79.4Improved
add path loss to edge plus multi-hop losses (ablation)DAGR · MTILAvg. accuracy: 76.2 -> 79.4Improved
add graph pruning to reduce cost (ablation)DAGR · MTILAvg. accuracy: 79.4 -> 78.8 (time 2.9 h -> 2.6 h)Hurt
add progressive regularization to reduce cost (ablation)DAGR · MTILAvg. accuracy: 79.4 -> 78.6 (time 2.9 h -> 2.7 h)Hurt
add both graph pruning and progressive regularization (ablation)DAGR · MTILAvg. accuracy: 79.4 -> 78.0 (time 2.9 h -> 2.3 h)Hurt
DAGR graph regularization versus DIKIprompt-based continual learning · MTILAvg. accuracy: 76.3 -> 79.4Improved
DAGR versus DIKI in 16-shot settingprompt-based continual learning · MTIL-FS (16-shot)Avg. accuracy: 71.9 -> 74.2Improved

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