AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

CAST: Context-Aware Dynamic Latent Space Transformation for Interactive Text-to-Image Retrieval

Xuanzuo Lin, Min Zhang, Daizong Liu, Zhiwen Zuo, Xun Yang, Changting Lin, Xun Wang, Jianfeng Dong

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval

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 context-aware low-rank projector (CLP) (ablation)CAST on BLIP · VisDial (10-round avg)Recall@1: 48.44 -> 51.04Improved
add context-guided modulator (CGM) on top of CLP (ablation)CAST on BLIP · VisDial (10-round avg)Recall@10: 80.90 -> 82.05Improved
use low-rank decomposed projection instead of full context-aware matrix W (ablation)CLP · VisDial (10-round avg)Recall@10: 80.57 -> 82.05Improved
make projector context-aware instead of a shared context-agnostic W (ablation)CLP · VisDial (10-round avg)Recall@10: 79.18 -> 82.05Improved
use one shared projector rather than separate context-agnostic projectors per round (ablation)context-agnostic projection · VisDial (10-round avg)Recall@10: 75.52 -> 79.18Improved
make modulation strength context-guided instead of a learnable scalar (ablation)CGM · VisDial (10-round avg)Recall@10: 81.51 -> 82.05Improved
add CASR to PlugIR and ChatIRPlugIR, ChatIR · VisDialRecall@KImproved
add CASR to zero-shot BLIPBLIP · VisDialRecall@KImproved
dynamic latent space versus static space across dialogue roundsCAST vs ChatIR · VisDial Recall@1Recall@1: 42.78 -> 43.60 (round 1); 53.15 -> 57.56 (round 10)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