AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Instruction-Grounded Visual Projectors for Continual Learning of Generative Vision-Language Models

Hyundong Jin, Hyung Jin Chang, Eunwoo Kim

ICCV 2025 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 2 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 adaptive knowledge aggregation (AKA) (ablation)MVP · Captioning average, Transfer (Vicuna)RefCLIP-Score: 68.92 -> 76.16Improved
add adaptive knowledge aggregation (AKA) (ablation)MVP · Question answering average, Transfer (Vicuna)accuracy: 44.55 -> 50.89Improved
add adaptive knowledge aggregation (AKA) (ablation)MVP · Classification average, Last (Vicuna)accuracy: 85.53 -> 85.87No clear effect
add expert pruning (ablation)MVP w/o AKA · Captioning average, Last (Vicuna)RefCLIP-Score: 71.55 -> 76.70Improved
add expert pruning (ablation)MVP w/o AKA · Question answering average, Last (Vicuna)accuracy: 75.54 -> 76.17Improved
add activation bias reduction loss (ablation)MVP w/o AKA, Prune · Classification average, Last (Vicuna)accuracy: 3.31 -> 85.92Improved
add recommendation loss (ablation)MVP w/o AKA, Prune, L_bias · Classification average, Avg (Vicuna)accuracy: 58.51 -> 69.59Improved
add recommendation loss (ablation)MVP w/o AKA, Prune, L_bias · Question answering average, Avg (Vicuna)accuracy: 51.39 -> 51.68Improved
replace single projector with mixture of visual projectors and all components (ablation)MVP · Classification average, Last (Vicuna)accuracy: 1.49 -> 85.87Improved
add L_bias to the method without AKA and pruning (ablation)MVP w/o AKA, Prune · Classification average, Transfer (Vicuna)accuracy: 78.06 -> 78.34No clear effect
use ten GPT-4o generated instructions per task instead of one default instructionMVP · Classification average, Last (Vicuna)accuracy: 85.87 -> 84.99No clear effect
use ten generated instructions per task instead of defaultMVP · Captioning average, Transfer (Vicuna)RefCLIP-Score: 76.16 -> 72.64Hurt

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