World Model Research
Open research powering the world model. Foundations in distribution modeling, scaling laws, and simulation infrastructure.
Research Foundations
Distribution Modeling
SICK BIDE: Binary Implicit Distribution Encoding via GPU-optimized softmax integral computation.
Scaling Laws
Apogée: How world model capabilities scale with compute, data, and model size.
Information Theory
Extropy as predictive information. Signal density, volatility clustering, temporal dependencies.
GPU Infrastructure
Custom GPU kernels, Monte Carlo simulation, model evaluation pipelines.
World Modeling
Learned simulators capturing market dynamics: regime transitions, tail behavior, multi-horizon rollouts.
Research Papers
SICK BIDE: Softmax Integral Compute Kernel + Binary Implicit Distribution Encoding
Foundational framework for probability distributions from binary representations. GPU-accelerated softmax integral computation for exact Monte Carlo inference.
APOGÉE: Scaling Laws for Crypto Market Forecasting
Quantifying predictability limits in crypto markets. Scaling experiments across model size, dataset scope, and compute. Open benchmark for time-series forecasting.
RESEARCH PRINCIPLES
OPEN-SOURCE ETHOS
- Core libraries and tools released under open licenses
- Reproducible pipelines and training scripts
- Modular design for community reuse and benchmarking
CALIBRATED EVALUATION
- Probabilistic scoring metrics (extropy, CRPS, proper scoring rules)
- Multi-horizon evaluation for short- and long-term reliability
- Time-series aware validation with no look-ahead bias
SCIENTIFIC ENGINEERING
- Built for integration: APIs, SDKs, and CLI tools
- GPU-accelerated by default for scalability
- Infrastructure tested under real-world constraints
Research Collaboration
We partner with researchers building world models for markets.