works on
frequency-domain representation 1multimodal large language models 1spatial-temporal trade-off 1temporal DCT 1video token compression 1

From the 1 of 6 linked papers with an AI index.

collaborators
Showing cs.AIShow all

1 paper · 1 filter

cs.AI2026

S1-Omni: A Unified Multimodal Reasoning Model for Scientific Understanding, Prediction, and Generation

Jiahao Zhao, Junyi Liu, Lifeng Xu +19

We present S1-Omni, a unified multimodal reasoning model for scientific understanding, prediction, and generation. AI for Science (AI4S) has advanced significantly through domain-s…