Penghao Wu

Expert
@penghao-wu

PhD Student @ NTU

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

707

visual_jigsaw. Python

78

GUI_Reflection. Python

34

ProxyV. [ICML 2025] Streamline Without Sacrifice - Squeeze out Computation Redundancy in LMM

20

gui_reflection_env. Python

2

cambrian. Cambrian-1 is a family of multimodal LLMs with a vision-centric design.

1

penghao-wu.github.io. HTML

1
7
Apply