AI Paper Atlas

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

PCLR: Progressively Compressed LoRA for Multimodal Continual Instruction Tuning

Weicheng Meng, Jingyang Qiao, Zhizhong Zhang, Shaohui Liu, Yuan Xie

ICLR 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Low-rank and model-merging adaptation

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 LoRA Rank Pool architecture with compression and learning (ablation)LoRA · CoIN LLaVA-1.5-7BAvg.ACC / Forgetting: Avg.ACC +25.92, Forgetting -26Improved
add integration process (distillation after compression) (ablation)PCLR · CoIN LLaVA-1.5-7BAvg.ACC / Forgetting: 54.66 -> 60.78 Avg.ACC; 11.29 -> 5.09 ForgettingImproved
add progressive learning process (ablation)PCLR · CoIN LLaVA-1.5-7BAvg.ACC / Forgetting: 60.78 -> 62.19 Avg.ACC; 5.09 -> 3.39 ForgettingImproved
use progressive compression instead of aggressive compression (ablation)PCLR · CoIN LLaVA-1.5-7BForgetting: 5.09 -> 3.39Improved
use progressive compression instead of conservative compression (ablation)PCLR · CoIN LLaVA-1.5-7BNew.ACC: 63.43 -> 65.16Improved
use progressive compression instead of reverse progressive (ablation)PCLR · CoIN LLaVA-1.5-7BAvg.ACC: 61.26 -> 62.19Improved
use progressive compression instead of centralized compression (ablation)PCLR · CoIN LLaVA-1.5-7BAvg.ACC: 61.00 -> 62.19Improved
increase integration data usage from none to 5k samples (ablation)PCLR · CoIN LLaVA-1.5-13BAvg.ACC / Forgetting: 59.40 -> 64.50 Avg.ACC; 8.86 -> 3.11 ForgettingImproved
use full dataset instead of 5k for integration (ablation)PCLR · CoIN LLaVA-1.5-13BAvg.ACC / Forgetting: 64.50 -> 65.51 Avg.ACC; 3.11 -> 2.08 Forgetting; 11 min -> 115 min costImproved
combine PCLR with LwF within task groups (ablation)PCLR · Continual-NExT LLaVA-1.5-hfAvg.ACC / Forgetting: 47.94 -> 52.67 Avg.ACC; 7.71 -> 4.58 ForgettingImproved
change instruction templates (Diverse, 10Type) (ablation)PCLR · CoIN LLaVA-1.5-7BAvg.ACC: 62.19 -> 62.00 and 61.98No clear effect
change task order (Reverse, Alphabet) (ablation)PCLR · CoIN LLaVA-1.5-7BAvg.ACC: 62.19 -> 62.18 and 60.62No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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