Researchers release paper on internal mechanisms of LOB state-space foundation models
Get up to speed
Researchers including Valentin Mohl published a research paper on the internal mechanisms of state-space foundation models for limit order books (LOB). The study shows that the 8.2M-parameter Mamba-3 model, after autoregressive training on limit order book message streams for 8 large-cap US stocks, can learn general internal representations of market microstructure. The model decodes order flow imbalance with an R² of approximately 0.59, significantly higher than control groups and baselines; the representation generalizes to unseen stocks and is causally manipulable. This paper has been accepted by the 7th ACM International Conference on AI in Finance (ICAIF '26).
AI-generated from reports · 1 hr agoUpdated
Coverage timeline
Follow the coverage to understand different sides of the event.
- arXiv q-finUnderstanding the Internal Mechanisms of State Space Foundation Models for Limit Order Books
A study on the 8.2M-parameter Mamba-3 state space model shows that after autoregressive training on limit order book message streams of 8 large-cap US stocks, the model can learn general internal representations of market microstructure. The model achieves an R² of approximately 0.59 for order flow imbalance decoding, significantly higher than control groups and baselines. The representations can generalize to unseen stocks and exhibit causal controllability. This paper has been accepted by the 7th ACM International Conference on AI in Finance (ICAIF '26).
Trend of this event
Not enough consecutive observations yet; trend is not drawn.