Microsoft ResearchUnited States2026

Rho-alpha

Key figures as stated by the developer

4 of 7 key figures stated

Controls ⁠A arms and hands
Inputs ⁠A camera language robot state touch
Access ⁠A Partners / early access only
Base model ⁠A Phi vision-language model (version not named)

Not stated: Model type · Parameters · Licence

Full specifications

6 of 14 fields stated

The letter points to the source at the foot of the page. Fields without a figure are dashed: the developer does not state them — that is not the same as zero, and not the same as no.
Field	Value	Source and caveats
Release
Released	21 January 2026	[A] Publication date in the page metadata: "2026-01-21T04:00:05+00:00". ⁠A
Input and output
Model type	not stated	Note Microsoft Research's own term: "It can be described as a VLA+ model in that it expands the set of perceptual and learning modalities beyond those typically used by VLAs". ⁠A
Inputs	`camera` `language` `robot state` `touch`	Microsoft Research: "Rho-alpha translates natural language commands into control signals for robotic systems performing bimanual manipulation tasks"; "For perception, Rho-alpha adds tactile sensing". The Foundry Labs page lists "multimodal sensing (vision, proprioception, touch)". ⁠A
Controls	`arms and hands`	Microsoft Research: "Rho-alpha translates natural language commands into control signals for robotic systems performing bimanual manipulation tasks". ⁠A
Degrees of freedom controlled	not stated
Size and speed
Parameters	not stated
Control rate	not stated
Where it runs and what it is built on
On robot or cloud	not stated	Note Microsoft names cloud-hosted use as its aim: "train, deploy, and continuously adapt their own cloud-hosted physical AI using their own data for their own robots and scenarios". ⁠A
Base model	Phi vision-language model (version not named)	Microsoft Research: "our first robotics model derived from Microsoft’s Phi series". ⁠A
Openness
Access	Partners / early access only	Microsoft Research: "We invite organizations interested in evaluating Rho-alpha for their robots and use cases to express interest in the Rho-alpha Research Early Access Program". "Rho-alpha will also be made available via Microsoft Foundry at a later date". ⁠A
Licence terms	not stated
Licence	not stated
The developer’s own claims
Learns new tasks	not stated	Note Microsoft Research: "we are working toward enabling Rho-alpha to continually improve during deployment by learning from feedback provided by people". The Foundry Labs page: "the model learns continually from human teleoperation feedback during deployment". ⁠A
Works across robots	yes	Developer claim: "The model is currently under evaluation on dual-arm setups and humanoid robots". The footage shows "a tactile sensor-equipped dual-UR5e-arm setup controlled by Rho-alpha". ⁠A Yes only if the developer itself says the model runs on different robot models, for example robots from two manufacturers or two of one manufacturer’s models. Several units of the same robot do not count.

How to read the figures

50HzA: The letter in the grey square after a figure points to the source the figure came from. Pages with several sources carry several letters.

What the data labels mean

Notes

Microsoft Research calls Rho-alpha a VLA+ model: it adds tactile sensing to the usual vision, language and action.
Microsoft lists its address as Redmond, Washington, USA, in its privacy statement.

Versions and notes in the key figures (5)

Model type

Note Microsoft Research's own term: "It can be described as a VLA+ model in that it expands the set of perceptual and learning modalities beyond those typically used by VLAs".

Controls

Microsoft Research: "Rho-alpha translates natural language commands into control signals for robotic systems performing bimanual manipulation tasks".

Inputs

Microsoft Research: "Rho-alpha translates natural language commands into control signals for robotic systems performing bimanual manipulation tasks"; "For perception, Rho-alpha adds tactile sensing". The Foundry Labs page lists "multimodal sensing (vision, proprioception, touch)".

Access

Microsoft Research: "We invite organizations interested in evaluating Rho-alpha for their robots and use cases to express interest in the Rho-alpha Research Early Access Program". "Rho-alpha will also be made available via Microsoft Foundry at a later date".

Base model

Microsoft Research: "our first robotics model derived from Microsoft’s Phi series".

Sources

A Primary source. www.microsoft.com/en-us/research/story/advancing-ai-for-the-physical-world/ · Retrieved 2026-10-19

One line per source, not per figure: a source has one retrieval date. The letter beside a figure points to the line it came from.