๊ฐ€์ž… ํ›„ ์ดˆ๋Œ€ ๋งํฌ๋ฅผ ๊ณต์œ ํ•˜๋ฉด ๋™์˜์ƒ ์žฌ์ƒ ๋ฐ ์ดˆ๋Œ€ ๋ณด์ƒ์„ ๋ฐ›์„ ์ˆ˜ ์žˆ์Šต๋‹ˆ๋‹ค.

ModelScope
@ModelScope2022
Driving innovations with open communities. ๐Ÿ’ฌ Join our Discord:
๊ฐ€์ž… April 2024
183 ํŒ”๋กœ์ž‰ ์ค‘    16K ํŒฌ
Xiaomi-Robotics-U0-4B packs unified embodied world generation into a compact 4B model. ๐Ÿ“œ Apache 2.0. ๐Ÿค– ๐Ÿ“„ ๐Ÿ† The full U0 system ranks #1# on World Arena and lifts ฯ€0.5โ€™s real-world OOD success from 36.9% to 63.2% with generated data. ๐ŸŒ Generate or edit consistent multi-view scenes across robot embodiments. It also supports text-to-image and instruction-guided generation. ๐Ÿ›  Change objects, layouts, robot bodies, and camera views while preserving task structure and cross-view consistency. ๐Ÿง  Text, images, and embodied observations share one token space and next-token objective. Inference code and Gradio are included.
๋” ๋ณด๊ธฐ