AI Paper Atlas

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

KORE: Enhancing Knowledge Injection for Large Multimodal Models via Knowledge-Oriented Controls

Kailin Jiang, Hongbo Jiang, Ning Jiang, Zhi Gao, Jinhe Bi, Yuchen Ren, Bin Li, Yuntao Du, Lei Liu, Qing Li

ICML 2026 · Continual learning › Continual fine-tuning of LLMs · approach: Mixture-of-experts for multimodal continual tuning · 0 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 KORE-Augmentation (multi-round dialogue and instruction data) (ablation)KORE · EVOKE (LLaVA-v1.5 7B)K.A: 14.57 -> 35.96Improved
add KORE-Constraint (null-space adapter initialization) (ablation)KORE · EVOKE (LLaVA-v1.5 7B)K.R: 35.78 -> 40.00Improved
add KORE-Constraint (null-space adapter initialization) (ablation)KORE · EVOKE (LLaVA-v1.5 7B)K.A: 38.82 -> 35.96No clear effect
freeze matrix A in the null space (ablation)KORE · EVOKE (LLaVA-v1.5 7B)K.R: 38.92 -> 40.00Improved
use KORE-Augmentation instead of knowledge-aware text augmentation (ablation)KORE · EVOKE (LLaVA-v1.5 7B)K.A: 20.29 -> 38.82Improved
use KORE-Augmentation instead of knowledge-agnostic text augmentation (ablation)KORE · EVOKE (LLaVA-v1.5 7B)K.A: 15.60 -> 38.82Improved
use KORE-Augmentation instead of image augmentation (knowledge-aware) (ablation)KORE · EVOKE (LLaVA-v1.5 7B)HARS: 66.48 -> 79.04Improved
increase LoRA rank (ablation)KORE · EVOKE (LLaVA-v1.5 7B)overall performanceImproved
increase rank from 235 to 256 (ablation)KORE · EVOKE (LLaVA-v1.5 7B)Avg: 37.98 -> 39.14Improved
use KORE instead of Replay on larger modelLLaVA-v1.5 (13B) · EVOKE + retentionAvg: 30.91 -> 42.01Improved
use KORE instead of Replay on Qwen2.5-VL (7B)Qwen2.5-VL (7B) · EVOKE + retentionAvg: 39.53 -> 42.72Improved
use KORE instead of Replay in retentionLLaVA-v1.5 (7B) · EVOKE (LLaVA-v1.5 7B)K.R: 43.00 -> 40.00Hurt

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