Xiaomi Research
community
AI & ML interests
None defined yet.
Recent Activity
Papers
A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement
LociArt: A Unified Paradigm for Free-Style Local Video Stylization
SpatioLM is a parameter-efficient framework for improving spatial intelligence in vision-language models (VLMs). It introduces a plug-and-play spatio-
-
xiaomi-research/SpatioLM-Understanding-InternVL3.5
Image-Text-to-Text • 9B • Updated • 356 • 1 -
xiaomi-research/SpatioLM-Understanding-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 44 • 1 -
xiaomi-research/SpatioLM-Perception-InternVL3.5
Image-Text-to-Text • 9B • Updated • 39 • 1 -
xiaomi-research/SpatioLM-Perception-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 22 • 1
SpatioLM is a parameter-efficient framework for improving spatial intelligence in vision-language models (VLMs). It introduces a plug-and-play spatio-
-
xiaomi-research/SpatioLM-Understanding-InternVL3.5
Image-Text-to-Text • 9B • Updated • 356 • 1 -
xiaomi-research/SpatioLM-Understanding-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 44 • 1 -
xiaomi-research/SpatioLM-Perception-InternVL3.5
Image-Text-to-Text • 9B • Updated • 39 • 1 -
xiaomi-research/SpatioLM-Perception-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 22 • 1
spaces 4
Running
24
Xiaomi OCR 0
😻
Extract, parse, and understand documents from images
Running on Zero
MCP
4
MiLMMT-46 Translation (4B)
🌍
Multilingual translation across 46 languages with MiLMMT
Running on Zero
MCP
2
MiLMMT-46 Translation (1B)
🌍
Multilingual translation across 46 languages with MiLMMT
Running on Zero
MCP
10
MiLMMT-46 Translation (12B)
🌍
Multilingual translation across 46 languages with MiLMMT
models 32
xiaomi-research/Xiaomi-OCR-0
Image-Text-to-Text • 0.9B • Updated • 18.5k • 250
xiaomi-research/ProactiveMobile-Qwen2.5-VL-7B
Image-Text-to-Text • 849k • Updated • 187 • 3
xiaomi-research/milyte
Updated • 3
xiaomi-research/MiLMMT-46-4B-v1.0
Translation • 4B • Updated • 14.9k • 22
xiaomi-research/MiLMMT-46-12B-v1.0
Translation • 12B • Updated • 812 • 20
xiaomi-research/MiLMMT-46-1B-v1.0
Translation • 1.0B • Updated • 529 • 26
xiaomi-research/SpatioLM-Perception-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 22 • 1
xiaomi-research/SpatioLM-Perception-InternVL3.5
Image-Text-to-Text • 9B • Updated • 39 • 1
xiaomi-research/SpatioLM-Understanding-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 44 • 1
xiaomi-research/SpatioLM-Understanding-InternVL3.5
Image-Text-to-Text • 9B • Updated • 356 • 1