AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

Prompt Yourself: Awakening Textual Semantics in 1D Visual Tokenizers

Hualiang Wang, Siming Fu, Weinan Jia, Yuning Lu, Mu Liu, Jidong Jiang, Xiaomeng Li

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Recaptioning and text-supervised pretraining · 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 self-prompted alignment (SPA) (ablation)VLTok-B-L · ImageNet-1K valrFID: 0.90 -> 0.72Improved
add self-prompted alignment (SPA) (ablation)VLTok-B-L · ImageNet-1K val (MaskGIT)gFID: 2.08 -> 1.70Improved
add self-prompted alignment (SPA) (ablation)VLTok-B-L · ImageNet-1K vallinear probing accuracy: 66.2 -> 69.9Improved
use SigLIP2 text encoder instead of CLIP-B-16 (ablation)VLTok-B-L · ImageNet-1K valrFID: 0.81 -> 0.72Improved
use SigLIP2 text encoder instead of Qwen2.5-VL-7B (ablation)VLTok-B-L · ImageNet-1K valgFID: 2.01 -> 1.70Improved
use SigLIP2 text encoder instead of T5-XL (ablation)VLTok-B-L · ImageNet-1K valrFID: 0.75 -> 0.72Improved
use Qwen2.5-VL-7B captions instead of LLaVA-Next-3B (ablation)VLTok-B-L · ImageNet-1K valrFID: 0.82 -> 0.72Improved
use Qwen2.5-VL-7B captions instead of InternVL3-8B (ablation)VLTok-B-L · ImageNet-1K valgFID: 1.77 -> 1.70No clear effect
replace contrastive loss with SPA (ablation)VLTok-B-L (128 tokens) · ImageNet-1K valrFID: 1.26 -> 1.01Improved
add contrastive loss to VLTok without alignment (ablation)VLTok-B-L (128 tokens) · ImageNet-1K valrFID: 1.42 -> 1.26Improved
add SPA (out-of-domain) (ablation)VLTok-B-L · COCOrFID: 2.28 -> 1.29Improved
add SPA (out-of-domain) (ablation)VLTok-B-L · AFHQ-wildrFID: 14.29 -> 10.28Improved

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