SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2610.02208 · October 2026

Sphere Encoder 2

Tom Goldstein, Brian Bartoldson, Menglin Jia, Ruchit Rawal, Kaiyu Yue, Sean McLeish

arXiv · PDF

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Sphere Encoder is an autoencoder that generates images by decoding random points from a high-dimensional latent sphere. We identify two limitations of the original formulation that reduce its generation quality. First, random points concentrate near the equator relative to the pole on an encoded latent, but the training rotation never reaches this region, leaving a gap that limits one-step generation. Second, training for generation with pixel-wise reconstruction loss encourages the decoder to average over plausible images, producing blurry images that lack high-frequency details. We present Sphere Encoder 2 to address both limitations, substantially improving image generation quality while maintaining the speed and simplicity of a autoencoder. Models are released at \href{https://github.com/kaiyuyue/sphere2}{github.com/kaiyuyue/sphere2}.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2610.02208")
get_code_for_paper("2610.02208")
have("2610.02208")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2610.02208.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2610.02208.svg)](https://syntology.ai/paper/2610.02208)

Connect an agent — have() is free.