AI Paper Atlas

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

Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document Retrieval

Weiqing Li, Jinyue Guo, Yaqi Wang, Haiyang Xiao, Yuewei Zhang, Guohua Liu, Hao Henry Wang

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 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 multi-view alignment (MVA) (ablation)Net0 baseline · ViDoRe V2 (3B)nDCG@5: 61.17 -> 62.25Improved
use downsample-only augmented view instead of dual view (ablation)MVA · ViDoRe V2 (3B)nDCG@5: 61.17 -> 59.75Hurt
use stitched-only view without original view (ablation)MVA · ViDoRe V2 (3B)nDCG@5: 61.17 -> 58.59Hurt
add bidirectional contrastive learning (BCL) with fixed hard negatives (ablation)Net0 baseline · ViDoRe V2 (3B)nDCG@5: 61.17 -> 61.84Improved
combine MVA and BCL (ablation)Net0 baseline · ViDoRe V2 (3B)nDCG@5: 61.17 -> 62.39Improved
use fixed window 80-98% negatives (ablation)Net0 baseline · ViDoRe V2 (3B)nDCG@5: 61.17 -> 62.10Improved
use dynamic rule-based oracle curriculum instead of fixed window (ablation)Fixed Window 80-98% · ViDoRe V2 (3B)nDCG@5: 62.10 -> 62.81Improved
use LLM-EC instead of rule-based oracle (ablation)Rule-based Oracle · ViDoRe V2 (3B)nDCG@5: 62.81 -> 63.05Improved
add exploration phase (ablation)LLM-EC · ViDoRe V2 (3B)nDCG@5: 61.86 -> 63.05Improved
use 16 intervals instead of 21 intervals (ablation)LLM-EC · ViDoRe V2 (3B)nDCG@5: 62.15 -> 63.05Improved
use Qwen3-32B controller instead of Qwen3-235B-A22B (ablation)LLM-EC · ViDoRe V2 (3B)nDCG@5: 63.05 -> 63.30No clear effect
use margin-loss temperature 0.02 instead of 1.0 (ablation)Evo-Retriever 3B · ViDoRe V2 (3B)nDCG@5: 57.37 -> 63.05Improved

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