nowfound

Life & fun · April 25, 2026

SC

ShadowPEFT – Centralized and Detachable Parameter-Efficient Fine-Tuning

Unlike LoRA and its variants, which inject trainable parameters directly into the weights of the Transformer, requiring tight coupling with the backbone. ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network. This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud…

What it does

In the maker’s words, at launch

Unlike LoRA and its variants, which inject trainable parameters directly into the weights of the Transformer, requiring tight coupling with the backbone. ShadowPEFT instead enhances the frozen large base model by adding a lightweight, centralized, pretrainable, and detachable Shadow network. This shadow network operates in parallel with the base model, delivering learned corrections to each decoder layer. Because the shadow module is architecturally decoupled from the backbone, it can be independently trained, stored, and deployed, benefiting edge computing scenarios and edge-cloud collaboration computing.

Does the same job

all alternatives →
  • Predibase Reinforcement Fine-Tuning2025 · ▲175

    LLM reinforcement fine-tuning platform to improve LLM output

  • TinkerOct 2025 · ▲125

    Control every aspect of model training and fine-tuning

  • Mistral Medium 3.5Apr 2026 · ▲123

    A 128B model for coding, reasoning, and long tasks

  • DeepSeek-V3.1-TerminusSep 2025 · ▲148

    A refined agentic model for developers

  • Monostate AItrainingDec 2025 · ▲59

    Fine-tuning, RL, and inference in one CLI

  • BH
    Beating Hinton et al.'s capsule net with fewer params and less training2019 · ▲14

    Hello HN, I recently posted a work-in-progress paper, along with code necessary for replicating all its results, at: https://github.com/glassroom/heinsen_routing Among other things, the code in this repo outperforms Hinton et al.'s recent state-of-the-art result in visual recognition[0] while requiring fewer parameters and an order-of-magnitude fewer training epochs. Most of the original research we do at work tends to be either proprietary in nature or tightly coupled to internal code, so we cannot share it with the world. In this case, however, I was able to remove all…

More life & fun this month

the category →
  • TL

    Life & fun · 10d ago · louisabraham.github.io

  • Photosynthesis fires two of your iPhone

    Life & fun · 28d ago · photosynthesis.camera

  • SoloUno310

    Take control of hair pulling, nail biting & skin picking

    Life & fun · 28d ago · solouno.io

  • Scroll through all 43,252,003,274,489,856,000 reachable Rubik's Cube permutations.

    Life & fun · 26d ago · everycube.alen.is

  • The Interactive 3D Encyclopedia

    Life & fun · 21d ago · expeditione.fun

  • Hi HN, I built Eigendrum, a web tool that solves the 2D wave equation for arbitrary shapes so you can hear what they sound like as drums. How it works: * Solves -∇²u = λu using finite element analysis (Kφ = λMφ) on a triangle mesh. * Validated to <0.1% error against closed-form solutions for circles (Bessel zeros) and rectangles. * Sound model factors in strike location, Rayleigh damping, and mallet width. * Includes Kac drums I & II to demonstrate identical sound spectra from different geometries. * No frameworks, build steps, or dependencies. Repo and tests:…

    Life & fun · 26d ago · baselashraf81.github.io

Launched alongside, April 2026

the whole month →
  • Brila1,367

    One-page websites from real Google Maps reviews

    AI · Apr 2026 · brila.ai

  • AG

    Thought the resources for GPU arch were lacking, so here we are

    Life & fun · Apr 2026 · jaso1024.com

  • IB

    Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.

    AI · Apr 2026 · github.com

  • AI meeting notes: now bot-free, in ChatGPT & Claude + more

    AI · Apr 2026 · fathom.ai

  • BC

    Life & fun · Apr 2026 · sam-burns.com

  • IB

    With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https:&#x2F;&#x2F;text.blogosphere.app&#x2F; Non-minimal: https:&#x2F;&#x2F;blogosphere.app&#x2F; If you don't find your blog (or your favorite ones), please add them. I will review and approve it.

    AI · Apr 2026 · text.blogosphere.app