AI Paper Atlas

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

WISER: Wider Search, Deeper Thinking, and Adaptive Fusion for Training-Free Zero-Shot Composed Image Retrieval

Tianyue Wang, Leigang Qu, Tianyu Yang, Xiangzhao Hao, Yifan Xu, Haiyun Guo, Jinqiao Wang

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Attribute-based zero-shot learning · 4 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 verifier-based fusion instead of fixed-weight averaging (ablation)WISER T2I+I2I · CIRCO mAP@5 (ViT-B/32)mAP@5: 13.53 -> 31.32Improved
fixed-weight AVG fusion of T2I and I2I vs T2I only (ablation)WISER · CIRCO mAP@5 (ViT-B/32)mAP@5: 17.28 -> 13.53Hurt
add adaptive fusion over both paths (ablation)WISER · Fashion-IQ val avg R@10 (ViT-B/32)R@10: 33.40 -> 40.83Improved
add Deeper Thinking on top of adaptive fusion (ablation)WISER · Fashion-IQ val avg R@10 (ViT-B/32)R@10: 40.83 -> 41.99Improved
add Deeper Thinking on top of adaptive fusion (ablation)WISER · CIRCO mAP@5 (ViT-B/32)mAP@5: 31.32 -> 32.23Improved
add Deeper Thinking to the T2I-only path (ablation)T2I baseline · Fashion-IQ val avg R@10 (ViT-B/32)R@10: 28.59 -> 29.22Improved
add Wider Search (use both T2I and I2I with adaptive fusion) vs T2I alone (ablation)WISER · CIRCO mAP@5 (ViT-B/32)mAP@5: 17.28 -> 31.32Improved
use stronger editor model alone (BAGEL T2I) vs CIReVL (ablation)T2I baseline · Fashion-IQ R@10R@10: 28.59 vs 28.27No clear effect
swap refiner LLM (Qwen-Turbo, GPT-3.5, GPT-4o-Mini, GPT-4o) (ablation)WISER · CIRCO mAP@5mAP@5: 32.21 to 32.80No clear effect
scale verifier from 3B to 7B (ablation)WISER · CIRCO mAP@5mAP@5: 27.50 -> 32.23Improved
scale verifier from 7B to 32B (ablation)WISER · CIRCO mAP@5mAP@5: 32.23 -> 31.69Hurt
swap editor (OmniGen2, Step1X-Edit, Bagel-Edit vs Bagel) (ablation)WISER · CIRCO mAP@5mAP@5: 31.18 to 32.23No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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