@sensetime_ai

AI-generated infographics with garbled text have been a running joke. SenseNova U1's new infographic-enhanced model finally fixes it, dense small text, correct charts, arXiv-style layouts. About time: huggingface.co/sensenova/Sen…

SenseNova U1 just released an infographic-specialized version and +18.2 on IGenBench Q-ACC isn't a rounding error. It means the model actually understands what information needs to go where. Real step forward: huggingface.co/sensenova/Sen…

Meet Xiaomai - the only staff member running a convenience store in Shanghai. From greeting customers and recommending products to processing payments and handing over purchases, this robot does it all on its own. #Shanghai #Robot #AI #Tech #Future #Innovation #SmartRetail #ChinaTech #Automation #Robotics Video

La mayoría de las herramientas de IA pueden escribir o generar imágenes. Pero esta hace AMBAS cosas a la vez. Te presentamos SenseNova U1. Una IA que piensa en texto e imágenes simultáneamente. Esto lo cambia todo 🧵

Excited to have contributed to the spatial intelligence capabilities of SenseNova-U1, surpassing strong baselines such as Qwen3.5 on key benchmarks including VSI-Bench. We’re also thrilled to open-source SenseNova-SI-8M, which is currently the largest spatial QA dataset to date. See you at CVPR this June, happy to chat in person! SenseNova-SI-8M: huggingface.co/datasets/sens…

Proud to announce the release of the SenseNova U1 Tech Report — together with the a new set of model weights based on MoE. We hope this open release promotes transparency, reproducibility, and further innovation across the AI community. Huge thanks to the team for making this possible. 🚀

Instead of stitching models together, SenseNova U1 runs everything inside one unified system. Built on NEO-Unify, it treats text and images as part of the same space. No switching between components. No translation gaps. Just one model that understands and creates at the same time.

I gave it a topic. It came back with a full magazine-style infographic. Charts. Layout. Icons. Colour coding. Dense structured copy. That model is SenseNova U1. And it's open-source. 🧵