Compare

Shanghai AI Laboratory · robot AI model

RoboInter-VLM

China · 2026

Sources retrieved: 19 November 2026 (A, B, C)

Model type
Embodied reasoning⁠
Inputs
Camera Language⁠
Access
Open weights (download)⁠
Base model
Qwen2.5-VL-7B-Instruct⁠
Licence type
Free, commercial use⁠

White robot arm with a black gripper above a patterned carpet with marker pens, coloured blocks and a brown bowl in front of a whiteboard

Specifications

7 of 14 stated 7 not stated

How to read the figuresShow guideClose
  • not statedNo source
  • 0Reported as zero
  • ASource

Select a source marker for source details and notes.

Release1/1 disclosed

Released10 February 2026

Input and output2/4 disclosed

Model typeEmbodied reasoning
InputsCamera Language
What it controlsNot stated
Degrees of freedom controlledNot stated

Size and speed0/2 disclosed

ParametersNot stated
Control rateNot stated

Where it runs and what it is built on1/2 disclosed

On robot or cloudNot stated
Base modelQwen2.5-VL-7B-Instruct

Openness3/3 disclosed

Licence documentApache-2.0
Licence typeFree, commercial use

The developer’s own claims0/2 disclosed

Learns new tasksNot stated
Works across robotsNot stated

Notes

Developed by researchers at USTC, Beihang University, and Shanghai AI Laboratory under InternRobotics.

Fine-tuned on RoboInter-VQA for intermediate representation understanding and generation in robotic manipulation.

Sources

One line per source, not per figure: a source has one retrieval date.

  1. Ahuggingface.co/InternRobotics/RoboInter-VLMMain source. Retrieved 19 November 2026
  2. Bgithub.com/InternRobotics/RoboInterRetrieved 19 November 2026
  3. Chuggingface.co/papers/2602.09973Retrieved 19 November 2026

Wrong or missing data? Tell us

More models

Same developer

Same model type