EN | 中文

SenseNova-SI: Scaling Spatial Intelligence with Multimodal Foundation Models

Overview

Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel). We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M: eight million diverse data samples under a rigorous taxonomy of spatial capabilities. SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks, while maintaining strong general multimodal understanding. More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training, analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. SenseNova-SI is an ongoing project, and this report will be updated continuously. All newly trained multimodal foundation models are publicly released to facilitate further research in this direction. In the future, SenseNova-SI will be integrated with larger-scale in-house models.

Models Zoo

Release Information

Currently, we build SenseNova-SI upon popular open-source foundation models to maximize compatibility with existing research pipelines. In this release, we present SenseNova-SI-1.4-InternVL3-8B, SenseNova-SI-1.3-InternVL3-8B, SenseNova-SI-1.2-InternVL3-8B, SenseNova-SI-1.1-Qwen2.5-VL-3B, SenseNova-SI-1.1-Qwen2.5-VL-7B, and SenseNova-SI-1.1-Qwen3-VL-8B. SenseNova-SI-1.4-InternVL3-8B demonstrates strong spatial intelligence across a wide range of benchmarks, with improved grounding performance, achieving an average score of 89.21 across all RefCOCO splits and 78.64 on CountBench. On our depth estimation task constructed from the Ibims dataset, it reaches 95.56 in relative depth and 80.31 in absolute depth.

For grounding and depth estimation benchmarks, we report the following results. RefCOCO and CountBench are reproduced using lmms-eval, while the depth estimation results are evaluated on our internally constructed test set.

🛠️ QuickStart

Installation

We recommend using uv to manage the environment.

uv installation guide: https://docs.astral.sh/uv/getting-started/installation/#installing-uv

git clone git@github.com:OpenSenseNova/SenseNova-SI.git
cd SenseNova-SI/
uv sync --extra cu124 # or one of [cu118|cu121|cu124|cu126|cu128|cu129], depending on your CUDA version
uv sync
source .venv/bin/activate

Hello World

A simple image-free test to verify environment setup and download the model.

python example.py \
  --question "Hello" \
  --model_path sensenova/SenseNova-SI-1.4-InternVL3-8B

Examples

Example 1

This example is from SITE-Bench:

python example.py \
  --image_paths examples/Q1_1.png \
  --question "Consider the real-world 3D locations of the objects. Which is closer to the sink, the toilet paper or the towel?\nOptions: \nA. toilet paper\nB. towel\nGive me the answer letter directly. The best answer is:" \
  --model_path sensenova/SenseNova-SI-1.4-InternVL3-8B

Details of Example 1

Q:Consider the real-world 3D locations of the objects. Which is closer to the sink, the toilet paper or the towel?\nOptions: \nA. toilet paper\nB. towel\nGive me the answer letter directly. The best answer is:

GT: A

Example 2

This example is from MMSI-Bench:

python example.py \
  --image_paths examples/Q2_1.png examples/Q2_2.png \
  --question "If the landscape painting is on the east side of the bedroom, where is the window located in the bedroom?\nOptions: A. North side, B. South side, C. West side, D. East side\nAnswer with the option's letter from the given choices directly. Enclose the option's letter within ``." \
  --model_path sensenova/SenseNova-SI-1.4-InternVL3-8B

Details of Example 2

Q:If the landscape painting is on the east side of the bedroom, where is the window located in the bedroom?\nOptions: A. North side, B. South side, C. West side, D. East side\nAnswer with the option's letter from the given choices directly. Enclose the option's letter within ``.

GT: C

Example 3

This example demonstrates the model's grounding capability, from RefCOCO:

python example.py \
  --image_paths examples/Q3_1.png \
  --question "Please provide the bounding box coordinate of the region this sentence describes: <ref>blue shirt lady</ref>" \
  --model_path sensenova/SenseNova-SI-1.4-InternVL3-8B

Details of Example 3

Q: Please provide the bounding box coordinate of the region this sentence describes: <ref>blue shirt lady</ref>

GT: [0.096234, 0.161229, 0.436516, 1.000000]

Example 4

This example demonstrates the model's depth estimation capability:

python example.py \
  --image_paths examples/Q4_1.png \
  --question "Identify the minimal distance between the point and the camera, in meters." \
  --model_path sensenova/SenseNova-SI-1.4-InternVL3-8B

Details of Example 4

Q: Identify the minimal distance between the point and the camera, in meters.

GT: 4.4

Evaluation

To reproduce the benchmark results above, please refer to EASI to evaluate SenseNova-SI on mainstream spatial intelligence benchmarks.

🖊️ Citation

@InProceedings{sensenova-si,
  title = {Scaling Spatial Intelligence with Multimodal Foundation Models},
  author = {Cai, Zhongang and Wang, Ruisi and Gu, Chenyang and Pu, Fanyi and Xu, Junxiang and Wang, Yubo and Yin, Wanqi and Yang, Zhitao and Wei, Chen and Sun, Qingping and Zhou, Tongxi and Li, Jiaqi and Pang, Hui En and Qian, Oscar and Wei, Yukun and Lin, Zhiqian and Shi, Xuanke and Deng, Kewang and Han, Xiaoyang and Chen, Zukai and Fan, Xiangyu and Deng, Hanming and Lu, Lewei and Pan, Liang and Li, Bo and Liu, Ziwei and Wang, Quan and Lin, Dahua and Yang, Lei},
  booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year = {2026}
}