NEO-unify: Building Native Multimodal Unified Models End to End
•
146
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Demystifing Video Reasoning
SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning
Articles
Scaling Spatial Intelligence with Multimodal Foundation Models
-
sensenova/SenseNova-SI-1.5-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 1.51k • 3 -
sensenova/SenseNova-SI-1.4-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 908 • 3 -
sensenova/SenseNova-SI-1.3-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 368 • 9 -
sensenova/SenseNova-SI-1.3-Qwen3-VL-8B
Image-Text-to-Text • 9B • Updated • 2.01k • 2
SenseNova-U1: Unifying Multimodal Understanding and Generation with NEO-Unify Architecture
Scaling Spatial Intelligence with Multimodal Foundation Models
-
sensenova/SenseNova-SI-1.5-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 1.51k • 3 -
sensenova/SenseNova-SI-1.4-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 908 • 3 -
sensenova/SenseNova-SI-1.3-InternVL3-8B
Image-Text-to-Text • 8B • Updated • 368 • 9 -
sensenova/SenseNova-SI-1.3-Qwen3-VL-8B
Image-Text-to-Text • 9B • Updated • 2.01k • 2