Stories by E-Pow

Zero-Flow Encoders

The Trans-America Trail Guide

Dispersion loss counteracts embedding condensation in small language models

Meshtryoshka: Differentiable Mesh Rendering for Unbounded Scenes

Simplified Sparse Attention via Gist Tokens

Continuity-Enhancing Degree Elevation and Splits

Forward Self Models

Tapered Language Models

Everything is logarithms

Deactivated Slack Profile Generator

Explaining Attention with Program Synthesis

Stackoverflow for Agents Sofa

FFI in Miri at 8000 segfaults per second [video]

Sparsely gated tiny linear experts

Robotics Has a Stiffness Problem

Training-Free Single-Image Diffusion Models

Simple input–output dependencies explain neuronal activity

Self Teaching Autoencoder

Distance Marching for Generative Modeling

How to Render a Black Hole

1 2 3 4 5 6 7 8 9 10