AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Omni-Attribute: Open-vocabulary Attribute Encoder for Visual Concept Personalization

Tsai-Shien Chen, Aliaksandr Siarohin, Gordon Guocheng Qian, Kuan-Chieh Jackson Wang, Egor Nemchinov, Moayed Haji-Ali, Riza Alp Guler, Willi Menapace, Ivan Skorokhodov, Anil Kag, Jun-Yan Zhu, Sergey Tulyakov

CVPR 2026 · Vision-language and multimodal › Human and embodied modeling · approach: Scene graph generation · 1 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 contrastive loss (Lcon) (ablation)Omni-Attribute · 1K validation pairscosine-sim gap: -0.002 -> 0.608Improved
make MLLM trainable via LoRA instead of frozen (ablation)Omni-Attribute (no Lcon) · Attribute personalizationattribute fidelity: 0.494 -> 0.651Improved
make MLLM trainable via LoRA instead of frozen (ablation)Omni-Attribute (no Lcon) · Attribute personalizationtext fidelity: 0.920 -> 0.873Hurt
full finetuning instead of LoRA (ablation)Omni-Attribute (no Lcon) · Attribute personalizationaverage score: 0.774 -> 0.747Hurt
use 8 self-attention layers in connector instead of 1 linear layer (frozen MLLM) (ablation)Omni-Attribute (no Lcon) · Attribute personalizationaverage score: 0.745 -> 0.746No clear effect
increase contrastive weight and temperature (e, g) (ablation)Omni-Attribute · 1K validation pairs / attribute fidelitycosine-sim gap vs attribute fidelity: gap 0.738 vs 0.608, Attr-F 0.513 vs 0.641Mixed
use Omni-Attribute instead of CLIP, DINOv2, Qwen-VL encoders and editing modelsOmni-Attribute · 15-attribute personalization benchmarkconditioning fidelity / naturalness (MLLM and human)Improved

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