BLINK: Multimodal Large Language Models Can See but Not Perceive

arXiv:2404.12390v1 Announce Type: new
Abstract: We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the Blink tasks can be solved by humans "within a blink" (e.g., relative depth estimation, visual correspondence, forensics detection, and multi-view reasoning). However, we find these perception-demanding tasks cast significant challenges for current multimodal LLMs because they resist mediation through natural language. Blink reformats 14 classic computer vision tasks into …

abstract arxiv benchmark blink core cs.ai cs.cl cs.cv detection forensics found humans language language models large language large language models llms multimodal multimodal language models not found perception tasks type visual