5,535,879 AI resources indexedWorking toward the world’s largest AI resource index.

PDF

Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs

Research paper by Shengbang Tong and collaborators. Published 2024-06-24. Topics: multimodal LLMs, vision-centric approach, visual representation learning, visual instruction tuning, vision encoders.

Resource information

Authors
Shengbang Tong, Ellis Brown, Penghao Wu, Sanghyun Woo, Manoj Middepogu, Sai Charitha Akula, Jihan Yang, Shusheng Yang, Adithya Iyer, Xichen Pan, Austin Wang, Rob Fergus, Yann LeCun, Saining Xie
Research topics
multimodal LLMs, vision-centric approach, visual representation learning, visual instruction tuning, vision encoders, MLLM benchmarks, Spatial Vision Aggregator, CV-Bench, visual grounding
Publication date
2024-06-24
Publication
arXiv
Last record update
Nov 3, 2026