# Heptapod: Language Modeling on Visual Signals

Source: [Heptapod: Language Modeling on Visual Signals](<https://www.sota2.com/research/paper/68fa7bec1e209131cea8b53c>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-28T10:54:33.671Z

Authors: Yongxin Zhu, Jiawei Chen, Yuanzhe Chen, Zhuo Chen, Dongya Jia, Jian Cong, Xiaobin Zhuang, Yuping Wang, Yuxuan Wang

Published: 2025-10-08T05:54:46.000Z

## Abstract

We introduce Heptapod, an image autoregressive model that adheres to the foundational principles of language modeling. Heptapod employs \\textbf{causal attention}, \\textbf{eliminates reliance on CFG}, and \\textbf{eschews the trend of semantic tokenizers}. Our key innovation is \\textit{next 2D distribution prediction}: a causal Transformer with reconstruction-focused visual tokenizer, learns to predict the distribution over the entire 2D spatial grid of images at each timestep. This learning objective unifies the sequential modeling of autoregressive framework with the holistic self-supervised learning of masked autoencoding, enabling the model to capture comprehensive image semantics via generative training. On the ImageNet generation benchmark, Heptapod achieves an FID of $2.70$, significantly outperforming previous causal autoregressive approaches. We hope our work inspires a principled rethinking of language modeling on visual signals and beyond.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.06673>)

[PDF](<https://arxiv.org/pdf/2510.06673.pdf>)