BLINK_Benchmark icon indicating copy to clipboard operation
BLINK_Benchmark copied to clipboard

Published 20 hours ago • verified publisher icon zeyofu
→

Metadata

This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.org/abs/2404.12390 [ECCV 2024]

Results 4 BLINK_Benchmark issues
Sort by recently updated
recently updated
newest added

Coordinates of boxes and markers

Hi, Great and excellent work! I was wondering if it is possible to release the raw images without markers and also the coordinates for the markers and labels?

mahtabbigverdi avatar mahtabbigverdi

Suggestion to Include GPT-4o Results in Evaluation

Very helpful research, great worI wanted to express my appreciation for the excellent work your team has done in contributing significantly to the evaluation of visual language models. Your paper...

Halflifefa avatar Halflifefa

Test difference.

2 comment

![截屏2024-05-06 14 58 48](https://github.com/zeyofu/BLINK_Benchmark/assets/36093263/2e894224-0227-45d5-95d9-f9a1f084600d)

ApolloRay avatar ApolloRay

Feeding more than one image to LLaVA

1 comment

Hi, Thanks for the nice work! How do you feed 3 images to LLaVA for the visual similarity task? Thanks, Sara

SaraGhazanfari avatar SaraGhazanfari

← Metadata

102
Stars
6
Forks
Watchers

Owner

verified publisher icon zeyofu

Metadata

This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.org/abs/2404.12390 [ECCV 2024]

Back