Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

WaveletLM

wavelet-based, attention-free model with O(n log n) scaling

Details

External ID
47912249
Source
HN
Company
—
Product
WaveletLM
Website domain
github.com
Launched
April 26, 2026
Cohort
—
Upvotes
7
Upvotes percentile
0.38817480719794345
Tags
—
Fetched at
Sept. 7, 2026, 9:26 p.m.
Updated at
Sept. 7, 2026, 9:26 p.m.

Description

WaveletLM is a wavelet-based, attention-free architecture that replaces self-attention with learned lifting wavelet decomposition, a Fast Walsh-Hadamard Transform, per-scale gated spectral mixing with SwiGLU activation, an inverse FWHT, and wavelet reconstruction. Combined with expanded MLPs and sparse product-key memory, this yields a model with O(n log n) scaling in sequence length.With 23.8 PPL on WikiText-103, WaveletLM beats both GPT-2 Medium, which was trained on 80× more data, and Transformer-XL Standard, which uses recurrence to extend its effective context. It is undertrained and underregularized due to budget constraints, so there is much room for development and improvement.I invite anyone who is curious to examine the model, test it out, and extend its capabilities further. All code and weights are fully open source, and a PG-19 run will be completed in 2-3 days. Generations can be done in 4-5 GB VRAM at 28.8 tokens/second, and the model is trainable in 16.25 hours with 20 GB of VRAM, both on a 5090.README for comparison tables, instructions, logs, and future plans: https://github.com/ramongougis/WaveletLMWeights: https://huggingface.co/ragou19/WaveletLM/tree/mainGenerations: https://github.com/ramongougis/WaveletLM/blob/main/logs/wiki...The following samples were chosen for coherence, not factual accuracy. Factuality will require scaling and downstream techniques such as RAG and instruction tuning.> The history of the city is reflected in its architecture, which includes the historic Old Town and New Castle County Courthouse Square Historic District. The building was designed by John H. Stevens, who also designed the Albany-Fulton Celebration in 1906 and built a steel-hulled shipyard on the lake shore.> The album was released on August 25, 2007 by Sony Music Entertainment and features several songs from the record including "Never Say Die", "The Show", "Don't Cry for Me Argentina" and a cover of "I Can Only Imagine (But You Are Not Alone)".> The species was first described by Swedish zoologist Carl Linnaeus in 1758 as Agaricus adustus. The genus name is derived from the Latin words perma "to tie", and pous ("like") means "with a large head". In 1821, French mycologists Jean-Baptiste de Lacaille placed it in section Cricetae of the order Carnivora. He later renamed it Spongiforma punctata after the Greek kribensis.

Enrichment

Theme
scientific computing and research algorithms
Vertical
Horizontal
Function
Model & infra
Audience
Developer
AI stance
AI-native
Project type
Hobby / open-source project
Normalized one-liner
wavelet-based language model with efficient scaling
Manually corrected
False

Could you build this?

No This is novel deep learning architecture research combining lifting wavelet decomposition, Fast Walsh-Hadamard Transforms, and custom operator kernels, requiring ML research expertise and custom training pipelines.

What it would actually take: Building this requires developing novel PyTorch/Triton CUDA kernels for fast Walsh-Hadamard transforms and wavelet reconstruction, mathematical modeling of multi-scale spectral mixing, and large-scale pretraining compute on vast token datasets. It demands expertise in numerical signal processing, theoretical ML architecture design, and low-level GPU acceleration.

Discussion

1 comment analyzed.

Competitors mentioned: GPT-2, Transformer-XL

Competitors

Other products that read as similar to this one — 21 launches clear the similarity bar, closest 8 shown.

Attention rank: #13 of 22 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 177 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a model & infra tool for Fintech yet.