Hugging Face's logo
Roberto Tacconelli's picture
5 2 7

Roberto Tacconelli PRO

robtacconelli
djahfar's profile picture tylerwsl's profile picture branikita's profile picture
·

AI & ML interests

None yet

Recent Activity

liked a Space about 17 hours ago
robtacconelli/midicoth
reacted to their post with 🤯 1 day 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!
reacted to their post with 🚀 1 day 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!
View all activity

Organizations

None yet