AI Paper Atlas

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

KSS-MoE: Knowledge Space Synergy Framework in Mixture of Experts for Continual Visual Instruction Tuning

Lingyun Song, Ziyao Chen, Kang Pan, Xiaolin Han, Xinbiao Gan, Yudai Pan, Xiaofan Sun, Xiaoqi Wang, Xuequn Shang

AAAI 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
use KSS-MoE instead of O-LoRALLaVA-1.5-7B continual visual instruction tuning · CoIN (8 tasks)MAA (%): 52.61 -> 59.99Improved
use KSS-MoE instead of O-LoRALLaVA-1.5-7B continual visual instruction tuning · CoIN (8 tasks)BWT (%): -19.75 -> -11.25Improved
add the general expert with orthogonal shared space (ablation)KSS-MoE · CoIN (8 tasks)MAA (%): 57.64 -> 59.99Improved
add the general expert with orthogonal shared space (ablation)KSS-MoE · CoIN (8 tasks)BWT (%): -13.54 -> -11.25Improved
learn the general expert in an orthogonal shared space instead of a vanilla general expert (ablation)KSS-MoE · CoIN (8 tasks)MAA (%): 52.61 -> 59.99Improved
add a vanilla general expert without orthogonal projection (ablation)KSS-MoE without general expert · CoIN (8 tasks)MAA (%): 57.64 -> 52.61Hurt
add expert subspace collaboration instead of naive MoE routing (ablation)KSS-MoE · CoIN (8 tasks)MAA (%): 45.00 -> 57.64Improved
add expert subspace collaboration instead of naive MoE routing (ablation)KSS-MoE · CoIN (8 tasks)BWT (%): -21.83 -> -13.54Improved
increase LoRA rank from 4 to 16 (ablation)KSS-MoE · CoIN (8 tasks)MAA (%): 53.42 -> 59.99Improved
increase LoRA rank from 4 to 8 (ablation)KSS-MoE · CoIN (8 tasks)BWT (%): -11.89 -> -15.05Hurt
increase LoRA rank from 16 to 32 (ablation)KSS-MoE · CoIN (8 tasks)MAA (%): 59.99 -> 60.74No clear effect
vary relevance thresholds epsilon and gamma from 0 to 0.5 (ablation)KSS-MoE · CoIN (8 tasks)MAA and BWTMixed

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