SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2501.04670 · ICCV · 2025

Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs

Yunhai Tong, Xiangtai Li, Lu Qi, Shilin Xu, Tao Zhang, Jiangning Zhang, Qianyu Zhou, Shunping Ji, Yikang Zhou, Shihao Chen

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Answer 1: C Answer 2: The objects are the same because they both have similar positions and body orientations in the images. The cyan contour in the first image matches the position and orientation of the object marked with ID 3 in the second image.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2501.04670")
get_code_for_paper("2501.04670")
have("2501.04670")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2501.04670.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2501.04670.svg)](https://syntology.ai/paper/2501.04670)

Connect an agent — have() is free.