xiaomi-research/MiLMMT-46-4B-v1.0
Translation • 4B • Updated • 111 • 16
Xiaomi Research
community
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
From Synthesis to Removal: Physics-Grounded Reflection Simulation and Diffusion-Based Video Dereflection
Reference-Free Post-Training of Open Large Language Models for Multilingual Machine Translation
xiaomi-research/MiLMMT-46-12B-v1.0
Translation • 12B • Updated • 266 • 13
xiaomi-research/MiLMMT-46-1B-v1.0
Translation • 1.0B • Updated • 126 • 19
xiaomi-research/SpatioLM-Perception-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 20
xiaomi-research/SpatioLM-Perception-InternVL3.5
Image-Text-to-Text • 9B • Updated • 20
xiaomi-research/SpatioLM-Understanding-SenseNovaSI
Image-Text-to-Text • 8B • Updated • 31
xiaomi-research/SpatioLM-Understanding-InternVL3.5
Image-Text-to-Text • 9B • Updated • 52
xiaomi-research/SpatioLM-Action-VLA0
Image-Text-to-Text • 2B • Updated • 16
xiaomi-research/MiLMMT-46-4B-v0.1
Translation • 4B • Updated • 285 • 3
xiaomi-research/MiLMMT-46-1B-v0.1
Translation • 1B • Updated • 761 • 7
xiaomi-research/GemmaX2-28-9B-v0.2
Translation • 9B • Updated • 144 • 1
xiaomi-research/GemmaX2-28-2B-v0.2
Translation • 3B • Updated • 109 • 3
xiaomi-research/MiLMMT-46-12B-v0.1
Translation • 12B • Updated • 616 • 9
xiaomi-research/OneVL_mlp_NAVSIM
14B • Updated • 63
xiaomi-research/Baseline_cot_NAVSIM
570k • Updated • 13
xiaomi-research/Baseline_answer_NAVSIM
570k • Updated • 11
xiaomi-research/OneVL_visual_decoder_pt_ar1
Image-Text-to-Text • 5B • Updated • 10
xiaomi-research/OneVL_visual_decoder_pt
Image-Text-to-Text • 5B • Updated • 61
xiaomi-research/OneVL_ROADWork
Image-Text-to-Text • 14B • Updated • 27 • 1
xiaomi-research/OneVL_NAVSIM
Image-Text-to-Text • 14B • Updated • 116
xiaomi-research/OneVL_Impromptu
Image-Text-to-Text • 14B • Updated • 38
xiaomi-research/OneVL_AlpamayoR1
Image-Text-to-Text • 14B • Updated • 46 • 1
xiaomi-research/TTS-PRISM-7B
Audio Classification • 8B • Updated • 34
xiaomi-research/TTS-PRISM
Updated
xiaomi-research/MiLMMT-46-12B-Pretrain
Image-Text-to-Text • 12B • Updated • 17 • 1
xiaomi-research/MiLMMT-46-4B-Pretrain
Image-Text-to-Text • 4B • Updated • 51 • 2
xiaomi-research/MiLMMT-46-1B-Pretrain
Text Generation • 1B • Updated • 65 • 4
xiaomi-research/dggt
Updated
xiaomi-research/lego-edit
Updated • 1