Demian L. P.
very-cooluser
AI & ML interests
Anything that can run on ~3GB of memory is a instant thumbs up to me
Recent Activity
reacted to Keeby-smilyai's post with 🤗 about 1 hour ago
Hello everyone! reacted to robtacconelli's post with 🤯 2 days ago
🧬 Midicoth: diffusion-based lossless compression — no neural net, no GPU, no training data
What if reverse diffusion could compress text — without a neural network?
Midicoth brings score-based denoising into classical compression. It treats prior smoothing as forward noise and reverses it with Tweedie's formula on a binary tree — 3 denoising steps, James-Stein shrinkage, applied after all model blending. ~2,000 lines of C, single CPU core.
Beats every dictionary compressor we tested:
enwik8 (100 MB) → 1.753 bpb (−11.9% vs xz, −15% vs Brotli, −24.5% vs bzip2)
alice29.txt → 2.119 bpb (−16.9% vs xz)
Outperforms xz, zstd, Brotli, bzip2, gzip on all inputs
PAQ/CMIX still win with hundreds of models + LSTMs. LLM compressors win with pre-trained knowledge. Midicoth closes the gap with pure statistics — no mixer, no gradient descent, just counting.
The Tweedie denoising layer adds 2.3–2.7% on every file tested — the most consistent component in the ablation. Adding SSE or logistic mixers made things worse. In the online setting, count-based beats gradient-based.
No external dependencies. Fully deterministic. Bit-exact encode/decode. ~60 KB/s throughput.
💻 Code: https://github.com/robtacconelli/midicoth
📄 Paper: https://huggingface.co/papers/2603.08771
⭐ Space: https://huggingface.co/spaces/robtacconelli/midicoth
If you ever wondered whether diffusion ideas belong in data compression — here's proof they do. ⭐ appreciated! upvoted a collection 5 days ago
Qwen3-VLOrganizations
None yet