SenseNova Vision 7B MoT
SenseNova-Vision-7B-MoT is a unified multimodal model for computer vision. It reformulates object detection, OCR, referring localization, GUI grounding, keypoint detection, depth estimation, surface normal prediction, segmentation, and multi-view geometry as text, image, or mixed text-image generation, using natural language instructions instead of separate task-specific heads or decoders for each vision task.
- Type
- Multimodal
- Weights
- Open
- Downloads
- 320
- Likes
- 115
- Pipeline
- any to any
- License
- cc-by-nc-4.0
Model hub
sensenova/SenseNova-Vision-7B-MoT
- Repo
- sensenova/SenseNova-Vision-7B-MoT
- Access
- Public
Technical tags and languages
Papers
1
More from SenseTime
4
-
SenseNova 6.7 Flash-Lite
Multimodal
SenseNova 6.7 Flash-Lite is a lightweight multimodal agent model from SenseTime built for long horizon office…
-
13k DL
SenseNova U1 8B MoT
Multimodal
SenseNova-U1-8B-MoT is SenseNova’s open native multimodal model for unified image understanding, reasoning, g…
-
SenseNova U1 Pro
Image
Flagship image creation model from SenseTime's Riri Xin (SenseNova) family. Generates production ready visual…
-
SenseNova Unified Large Model
Text
Claude Haiku 4.5 is Anthropic’s fast, cost-efficient model. It handles everyday reasoning, coding, and multim…
About SenseTime
1
SenseTime is a leading Chinese AI company founded in 2014, specializing in computer vision, facial recognition, autonomous driving, smart city solutions, and generative AI.