cd /news/artificial-intelligence/thetascan-v0-1-open-scan-parallel-no… · home topics artificial-intelligence article
[ARTICLE · art-72298] src=discuss.huggingface.co ↗ pub= topic=artificial-intelligence verified=true sentiment=· neutral

ThetaScan v0.1: open scan-parallel nonlinear memory with preliminary 17M LM results

ThetaScan v0.1, a fixed-state nonlinear token mixer released by developer aim-do, achieves competitive bits-per-byte (BPB) on a 17M language-model experiment at step 7,500, with raw BPB of 1.2327 for the GN expanded 2× variant versus 1.2349 for attention. The open-source repository includes PyTorch library, technical paper, and reproduction configs, though the author cautions these are early single-seed results not claiming statistical superiority.

read1 min views1 publishedJul 24, 2026

I’m releasing ThetaScan v0.1, a research preview of a fixed-state nonlinear token mixer.

The central constraint is that every token computes its memory write from the current input and shared “slow” parameters—not from the evolving fast state. The writes therefore compose through an associative prefix scan, while the read remains nonlinear and query-dependent.

The public implementation contains:

Preliminary step-7,500 results from a single-seed, parameter-matched 17M language-model experiment:

Mixer Raw BPB Exact-int8 BPB
GN expanded 2× 1.2327
1.23831
GN dense 1.2342 1.23985
Attention 1.2349 1.24072
Kernel expanded 2× 1.2361 1.24215

These are early measurements, not a claim of statistical superiority: only one seed was tested, optimizer policies differ, and the current reference evaluator is quadratic rather than a fused linear-scaling implementation.

The repository includes the PyTorch library, technical paper, versioned recipes, tests, complete validation trajectories and staged reproduction configs.

I would especially welcome multi-seed replications, adversarial review of the write/read algebra, unified-optimizer comparisons, long-context failure tests and help with fused chunked kernels. Critical feedback and negative results are very welcome.

Repository: [https://github.com/aim-do/thetascan](https://github.com/aim-do/thetascan)

Paper: [https://github.com/aim-do/thetascan/blob/main/paper/ThetaScan-Scan-Parallel-Nonlinear-Memory.pdf](https://github.com/aim-do/thetascan/blob/main/paper/ThetaScan-Scan-Parallel-Nonlinear-Memory.pdf)
── more in #artificial-intelligence 4 stories · sorted by recency
── more on @thetascan 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/thetascan-v0-1-open-…] indexed:0 read:1min 2026-07-24 ·