OpenCodePapers
visual-document-retrieval-on-vidore-v2
Document Understanding
Visual Document Retrieval
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Show papers without code
Paper
Code
NDCG@5
↕
ModelName
ReleaseDate
↕
EVIE: High-Performance Multilingual Visual Document Retrieval with Matryoshka Embeddings and Token Compression
✓ Link
74.23
EVIE-8B
2026-09-07
ColNanoVDR: Document-Free Query Distillation for Multi-Vector Visual Document Retrieval via Optimal Transport
✓ Link
65.4
ColNanoVDR (from ColVec1.1-8b)
2026-09-28
NanoVDR: Distilling a 2B Vision-Language Retriever into a 70M Text-Only Encoder for Visual Document Retrieval
61.5
NanoVDR-L (ModernBERT, 151M)
2026-03-13
MetaEmbed: Scaling Multimodal Retrieval at Test-Time with Flexible Late Interaction
✓ Link
61.3
MetaEmbed-7B
2025-09-22
ModernVBERT: Towards Smaller Visual Document Retrievers
✓ Link
56.0
ColModernVBERT
2025-10-01
NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference
55.91
NeoMME-800M-Retriever (late interaction)
2026-08-31
M3DR: Towards Universal Multilingual Multimodal Document Retrieval
✓ Link
55.4000
NetraEmbed
2025-12-03
DistilVDR: A Compact End-to-End Visual Document Retriever via Dual-Student Distillation
✓ Link
55.34
DistilVDR-HiRes
2026-08-11
Generative Late-Interaction Embeddings For Visual Document Retrieval
✓ Link
49
GLIE (ColPali v1.3, k=64)
2026-09-10
Beyond the Grid: Layout-Informed Multi-Vector Retrieval with Parsed Visual Document Representations
32.86
ColParse (VLM2Vec-V1-2B)
2026-03-02
×