AI Paper Atlas

Research map / Vision-language and multimodal / Multimodal LLMs

Concept-as-Tree: A Controllable Synthetic Data Framework Makes Stronger Personalized VLMs

Ruichuan An, Kai Zeng, Ming Lu, Sihan Yang, Renrui Zhang, Huitong Ji, Hao Liang, Wentao Zhang

ECCV 2026 · Vision-language and multimodal › Multimodal LLMs · approach: VLM capability analysis · 9 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 synthetic data (CaT + PCS filter) to real dataMC-LLaVA · MC-LLaVA evalRecognition accuracy: 0.917 -> 0.963Improved
add synthetic data to real dataYo'LLaVA · MC-LLaVA evalRecognition accuracy: 0.841 -> 0.885Improved
add synthetic data to real dataMyVLM · MC-LLaVA evalRecognition accuracy: 0.795 -> 0.827Improved
train only on synthetic data instead of realMyVLM · MC-LLaVA evalRecognition accuracy: 0.795 -> 0.788Mixed
add synthetic data in multi-concept settingMC-LLaVA · MC-LLaVA eval (multi-concept)Recognition accuracy: 0.845 -> 0.881Improved
add PCS score filtering over no filtering (ablation)Yo'LLaVA + CaT · MC-LLaVA evalRecognition accuracy: 0.835 -> 0.885Improved
add PCS score filtering over cosine similarity filtering (ablation)Yo'LLaVA + CaT · MC-LLaVA evalRecognition accuracy: 0.862 -> 0.885Improved
add unfiltered synthetic data (ablation)Yo'LLaVA · MC-LLaVA evalRecognition accuracy: 0.841 -> 0.835Hurt
add attributes to the concept tree (1 to 2 Add operations) (ablation)Yo'LLaVA + CaT · MC-LLaVA evalRecognition accuracy: 0.841 -> 0.866Improved
add a third Add operation to the tree (ablation)Yo'LLaVA + CaT · MC-LLaVA evalRecognition accuracy: 0.866 -> 0.834Hurt
remove attributes from the concept tree (ablation)Yo'LLaVA + CaT · MC-LLaVA evalRecognition accuracy: 0.841 -> 0.801Hurt
add synthetic positives (ablation)Yo'LLaVA · MC-LLaVA evalRecognition accuracy: 0.841 -> 0.858Improved

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