AI Paper Atlas

Research map / Image generation / Autoregressive and latent generation

Less is More: Fewer Tokens and Blocks Make AIGI Detection Faster and More Generalizable

Haipeng Fang, Yixing Lu, Yu Li, Qiang Sheng, Juan Cao, Sheng Tang

NeurIPS 2026 · Image generation › Autoregressive and latent generation · approach: Generalizable fake image detection

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes removing rather than adding components to AIGI detectors, reducing tokens and blocks to make detection faster and more generalizable.

Problem

AI-generated image (AIGI) detectors often generalize poorly by relying on dataset-specific artifacts, and prior fixes add cost (extra artifact cues, pretraining, constraints, test-time operations).

Approach

Instead of adding modules, the method prunes tokens and transformer blocks to yield a smaller, faster detector that generalizes better across generators, based on a 'less is more' principle.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy