VL

VLM2Vec

Multimodal AI·application·open·#848 of 944·+15·Surging

58.9

Low

High confidence
WebsiteGitHub

This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks" [ICLR 2025]

Pillar Breakdown

Adoption

35%

52.6

Maintenance

30%

64.7

Friction

20%

99.2

Ecosystem

15%

27.1

Momentum

1.00Surging
7d change +0.39
High confidence

In Multimodal AI

Ranked #16 of 17

1MediaPipe
83.1
2serve
81.3
3LLaMA-Factory
80.9
4rerun
75.9
5LLaVA
74.3
6lmms-eval
70.8
7neuraltalk
69.8
8InternVL
68.6
See all 17 in Multimodal AI →

Similar Tools

OF

open_flamingo

Multimodal AI

58.9

DO

docarray

Multimodal AI

59.5

AV

Adaptive Vision-Language Model Routing

Multimodal AI

60.9

CO

CogVLM

Multimodal AI

64.0