Cellular Reasoning Fabric (CRF)

A bio-inspired alternative to the Transformer architecture for language modeling.

What is CRF?

The Cellular Reasoning Fabric replaces self-attention with a population of autonomous, communicating cells that:

Communicate via k-nearest-neighbor message passing (not global attention)
Split when energy is high (allocate more compute)
Die when energy is low (free resources)
Merge when states are similar (consolidate knowledge)
Uses O(N*k) routing instead of O(N^2) attention

Benchmark Results

Benchmark	CRF Perplexity	Transformer Perplexity	CRF Advantage
Synthetic	6.69	21.14	3.2x
ARC Reasoning	17.36	53.04	3.1x
Arithmetic	22.37	62.75	2.8x
Chain-of-Thought	21.96	60.10	2.7x
Code Generation	23.95	60.29	2.5x

Model Details

Property	Value
Parameters	33,890
d_model	64
d_hidden	32
Initial Cells	16
Max Cells	64
CRF Steps	4
k-Neighbors	3
FLOPs/forward	858,176

Dynamic Cell Population

The CRF model features a fully operational cell lifecycle:

Splits: 12-16 per forward pass (cells divide to add compute)
Merges: 2+ per forward pass (redundant cells consolidate)
Deaths: Cells with depleted energy are removed
Energy tracking: Diagnostic metrics for monitoring cell health

Usage

import torch
from src.crf_reasoning.crf_vectorized import CRFLanguageModel, AblationConfig

cfg = AblationConfig()
model = CRFLanguageModel(
    vocab_size=256,
    d_model=64,
    d_hidden=32,
    n_init_cells=16,
    max_cells=64,
    n_crf_steps=4,
    k_neighbors=3,
    cfg=cfg,
)

# Load weights
state_dict = torch.load("crf_model.pt", map_location="cpu")
model.load_state_dict(state_dict)

# Forward pass with metrics
x = torch.randint(0, 256, (1, 32))
logits, loss, metrics = model(x, targets=x, collect_metrics=True)
print(f"Splits: {metrics.n_splits}, Merges: {metrics.n_merges}")

Limitations

Small-scale experiments (d_model=64, seq_len=32, 400 training samples)
Single seed - multi-seed validation needed
Inference latency is 4-8x higher than Transformer
Not yet tested on large-scale benchmarks (MMLU, HumanEval)

Citation

If you use this work, please cite:

@misc{usman2026crf,
  title={Cellular Reasoning Fabric: A Bio-Inspired Alternative to Transformers},
  author={Yasir Usman},
  year={2026},
  publisher={Hugging Face},
  url={https://huggingface.co/YasirUsman/cellular-reasoning-fabric}
}

License

MIT

Downloads last month: 20

YasirUsman
/

cellular-reasoning-fabric