MLabs AI is an independent AI Research Lab with a focus on state of the art LLM research.
We operate as a high-throughput research engine. We continuously generate and test unconventional training approaches across multiple domains, failing fast and often, and refining those that expose unnecessary rigidity in current methods.
Our advantage is not a single method, but the rate at which we can explore the design space.
Through our process we have developed several new algorithms and mathematical constructions, including cases where parts of MLP training can be performed without gradient descent while improving accuracy and efficiency in specific regimes.
We have recently started work on factorized pre-trained transformers, separating the knowledge base, reasoning and language generation into separate modular components. This is a work in progress but boasts several potential advantages, including more efficient training, smaller footprint models, enhanced explainability and the ability to update the knowledge base without retraining the entire model.
Our research and development efforts are concentrated on key areas that drive the efficiency and capability of large language models.
Explicitly factoring the machine learning requirements for syntax, semantics, pragmatics and discourse.
Developing advanced methods for minimizing the loss function for the model or specific layers without the need for gradient descent.
Maximizing learning effectiveness through novel techniques for gradient signal and condition number optimization.
Innovating architectures to reduce actual or effective parameter counts while retaining or encouraging modelling capability.
Designing more effective methods for token prediction by optimizing over an extended prediction horizon.
Extending the effective context window while maximizing the information density and reducing computational load.
Our innovation pipeline has 50+ research directions to explore. We’re continuously reassessing which directions are worth pursuing, but below are some of our directions.
Gain (real-time) access to our current and past research, innovations and experiments, including valuable insights from negative results.
First right to acquire or license new innovations before they reach the wider market.
Influence our research roadmap to align with your strategic goals, ensuring our work addresses your most pressing challenges.
Monthly update call on our progress, discoveries and results.
Receive tailored research insights and direct feedback on your specific areas of interest from our leading AI scientists.
To discuss research partnerships please reach out to info@mlabsai.com
MLabs AI