Imperfective

Revealing the intelligence of the Universe

AI that understands how the physical world works.

Interactive studies of protein conformations, material grain growth, and a self-stabilising network. Five small explorers follow connections, share discoveries and leave their paths illuminated as Life, Matter and Civilization gradually change into one another. Scroll to move between scales, choose a scale with the buttons, or drag the structure. Pause stops the structure, explorers and light together.

Imperfective turns scientific and industrial data into reusable models of complex systems, helping scientists and engineers understand not just what happens, but why, what could change, and what to do next.

Mission

We want to expand what humanity can understand, discover and create.

We are building AI to discover the rules governing the physical world, from the movements of a single molecule to the operation of complex machinery and the behaviour of entire planetary systems. Our ambition is for it to uncover physics that humans have not yet discovered.

Every experiment, every observation and every simulation captures something about how the universe works. We believe AI can learn from this growing record to uncover relationships that have remained beyond our reach, and use each discovery to make the next one possible.

We call this approach Spectral Intelligence. It is the foundation of our ultimate goal, the Universal Spectral Model: AI that learns the structure of change, recognizing the principles shared in the physical world and using that knowledge to understand systems it has never encountered - from those familiar to humanity, to those beyond the boundaries of current knowledge.

This model will discover increasingly general principles from its experience, so what it learns about one system could unlock an understanding of another, connecting areas of science and engineering that we study separately today.

This would give us a new means of scientific discovery: AI that can uncover new physical laws and help us turn that understanding into technologies we do not yet know how to build.

Technology

We learn the structure of change

A protein folds, a machine vibrates, a fluid flows, and a weather system evolves. Humans and current AI observe these systems in extraordinary detail, and increasingly predict what they will do next. However, we still struggle to uncover the structure underneath that behavior: which patterns matter and recur, how quickly they change, how different states are connected, and when these relationships hold.

From harnessing the power of the Sun to making humanity healthier, scientists and engineers have spent decades collecting data, running simulations and conducting experiments. This work has created an enormous record of how complex systems behave and change over time.

Imperfective uses and builds upon these records to create genuinely differentiated computational and learning primitives.

Our product - the Spectral Operator Layer

Our product, the Spectral Operator Layer (SOL), brings Spectral Intelligence to scientific and engineering teams, working alongside the models, simulations and data they already have. SOL provides a reusable model for learning, simulating, interrogating and operating on dynamics.

Teams can use the resulting model to explore how a system behaves and decide where further simulation or experimentation is needed.

SOL is ready for deployment with frontier scientific and engineering teams.

One framework across different systems

Our founding researchers have applied the same underlying framework across molecular dynamics, industrial systems, weather and fluid dynamics, testing it with leading industrial companies across different physical scales.

It has been used to map states and pathways in a protein implicated in Alzheimer's disease; identify defective industrial behavior within the first seconds of operation; build weather forecasting models; and turn a small number of fluid simulations into a continuous space of dynamical models that can be explored in milliseconds.

The applications are deliberately different. The underlying technology is the same. Our technology works across these industries and applications.

A company or a scientific organization may have little data from any one experiment, configuration or design, but much more information across a population of related ones. If we learn what those systems share, we can use that information to reduce the data and work required to understand current systems and new ones.

This is the path toward our Universal Spectral Model: using what we learn from individual systems to build an understanding that extends across the physical world.

The next discovery

What could we discover together?

Meet Imperfective Work with us