Are They the Same? Exploring Visual Correspondence Shortcomings of Multimodal LLMs
🖥 Github: https://github.com/zhouyiks/CoLVA/tree/main
📕 Paper: https://arxiv.org/pdf/2501.04670v1.pdf
⭐️ Dataset: https://paperswithcode.com/dataset/bdd100k
@Machine_learn
Post #3273
2.19K
- 👍 1