penghao-wu/vstar

PyTorch Implementation of "V* : Guided Visual Search as a Core Mechanism in Multimodal LLMs"

2 best points · 0 comments · 1 Hacker News post · 715 GitHub stars · View on GitHub

Hacker News discussions

• V*: Guided Visual Search as a Core Mechanism in Multimodal LLMs (2 points, 0 comments, by saeedesmaili, 2024-01-13)