SOURCE-LINKED INTELLIGENCE

Efficient Training with Foresight: Multi-Token Auxiliary Supervision for Autoregressive Image Generation

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Autoregressive (AR) image generation has shown strong potential for scalable high-fidelity synthesis by modeling images as discrete token sequences. However, traditional next token prediction (NTP) continues to suffer from sparse and myopic supervision, insufficiently discriminative representations, and high training cost caused by dense computation over the full token sequence. To address these issues, we propose multi-token autoregressive (MTAR), a unified training framework that improves autoregressive image generation from three aspects: prediction objectives, representation regularization

Read original source ↗ Open in workspace

recordType

paper

region

Global