OneVL series vision-language models
Xiaomi Research
community
AI & ML interests
None defined yet.
Recent Activity
Papers
OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Video Streaming Thinking: VideoLLMs Can Watch and Think Simultaneously
models 21
xiaomi-research/OneVL_mlp_NAVSIM
14B • Updated • 14
xiaomi-research/Baseline_cot_NAVSIM
570k • Updated • 13
xiaomi-research/Baseline_answer_NAVSIM
570k • Updated • 14
xiaomi-research/OneVL_visual_decoder_pt_ar1
Image-Text-to-Text • 5B • Updated • 64
xiaomi-research/OneVL_visual_decoder_pt
Image-Text-to-Text • 5B • Updated • 79
xiaomi-research/OneVL_ROADWork
Image-Text-to-Text • 14B • Updated • 68
xiaomi-research/OneVL_NAVSIM
Image-Text-to-Text • 14B • Updated • 193
xiaomi-research/OneVL_Impromptu
Image-Text-to-Text • 14B • Updated • 56
xiaomi-research/OneVL_AlpamayoR1
Image-Text-to-Text • 14B • Updated • 85
xiaomi-research/TTS-PRISM-7B
Audio Classification • 8B • Updated • 65
datasets 0
None public yet