Ellis L Brown II — accepted AI-conference papers

2026

Towards Spatial Supersensing in Video

Shusheng Yang, Jihan Yang, Pinzhi Huang, Ellis L Brown II, Zihao Yang, Yue Yu +8

ICLR 2026poster

We frame spatial supersensing in video as an overarching goal for multimodal intelligence and argue that progress requires a shift from long-context brute force to predictive sensing. Using a four-level taxonomy: semantic perception, streaming event cognition, implicit 3D spatial cognition, and pred…

Cited by 0 Source ↗code ↗Scholar ↗

2024

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

Shengbang Tong, Ellis L Brown II, Penghao Wu, Sanghyun Woo, ADITHYA JAIRAM IYER, Sai Charitha Akula +8

NeurIPS 2024oral

We introduce Cambrian-1, a family of multimodal LLMs (MLLMs) designed with a vision-centric approach. While stronger language models can enhance multimodal capabilities, the design choices for vision components are often insufficiently explored and disconnected from visual representation learning re…

Cited by 321 Source ↗PDF ↗code ↗Scholar ↗