For research, collaboration, and signals from the field
Voir studies spatial intelligence: how machines perceive, measure, remember, simulate, and act within physical space.
The important thing is relation to the inquiry
If your work touches machine perception, synthetic data, augmented reality, robotics, embodied AI, spatial computing, accessibility, simulation, measurement, or the legibility of spaces, correspondence is welcome.
Not every message requires a finished proposal. A question may be enough. A paper may be enough. A prototype may be enough. A signal from the field may be enough.
What matters is relation to the inquiry, not the polish of the message. A clear question about how a system perceives, measures, remembers, or moves through space carries further than a finished pitch. Tell us what you are studying, what you are trying to measure, and where the work meets the physical world. The most useful correspondence tends to name a specific difficulty: a scene a model cannot read, a measurement it cannot trust, a place it cannot remember between sessions.
- How does intelligence become spatial?
- How does space become legible?
- How does computation become accountable to the physical world?
Find the channel closest to your work
For researchers, students, independent builders, labs, and institutions working near spatial intelligence
If your work studies how machines understand physical reality, send a note.
Some questions are better studied across disciplines
We welcome collaborations that clarify the field, research partnerships, field studies, prototype development, dataset work, technical writing, spatial interface studies, measurement systems, public demonstrations, independent experiments.
Across the disciplines →Voir's public instrument for synthetic visual data generation
Use this channel for questions, feedback, issues, examples, or use cases related to Spectrum, download questions, installation issues, dataset generation, Unity workflows, synthetic data use cases, texture randomization, camera and lighting variation, one-shot and few-shot learning, computer vision training, model testing, research feedback. If Spectrum helped you create a dataset, test a model, or study visual variation, Voir would be interested in seeing what it made possible.
Synthetic & world models →The field is forming across many places
If something appears relevant to spatial intelligence, send it as a signal. A strong signal does not need to be popular. It needs to reveal something.
Read a signal →Best understood through the language of research, not product hype
Spatial intelligence. Synthetic data. Machine perception. The legibility of spaces. Measurement and trust. Interfaces beyond screens. Embodied intelligence. The movement from symbolic awareness to spatial awareness.
Read the essay →Some messages will not fit a category. That is fine
If the inquiry belongs near the work, send it.
Measurement & trust →The strongest collaborations begin with a clear question
- What are you studying?
- What are you trying to measure?
- What does the system fail to understand?
- What part of space are you trying to make legible?
A strong signal does not need to be popular. It needs to reveal something
The field is forming across many places. If something appears relevant to spatial intelligence, send it as a signal
- What changed?
- What became visible?
- What did the system understand?
- What did it fail to understand?
- Why does it matter for perception, measurement, embodiment, memory, simulation, presence, or human spatial experience?
Send correspondence
Voir reviews correspondence according to relevance, clarity, and relation to the field
Messages connected to active research, Spectrum, Ledger signals, or serious collaboration inquiries are most likely to receive a response.