CIAR: Interval-based Collaborative Decoding for Image Generation Acceleration

Auto-regressive (AR) models have recently made notable progress in image generation, achieving performance comparable to diffusion-based approaches. However, their computational intensity and sequential nature impede on-device deployment, causing disruptive latency. We address this via a cloud-device collaboration framework $\mathbf{\text{CIAR}}$, which utilizes on-device self-verification to handle two key properties of visual synthesis: $\mathit{\text{the}}\mathit{\text{vast}}\mathit{\text{token}}\mathit{\text{vocabulary}}$ required for high-fidelity images and $\mathit{\text{inherent}}\mathit{\text{spatial}}\mathit{\text{redundancy}}$ which leads to extreme predictability in homogeneous regions, while object boundaries exhibit high uncertainty. Uniform verification wastes resources on such redundant tokens. Our solution centers on an on-device token uncertainty quantifier, which adopts continuous probability intervals to accelerate processing and make it feasible for large visual vocabularies instead of conventional discrete solution sets. Additionally, we incorporate a Interval-enhanced decoding module to further speed up decoding while maintaining visual fidelity and semantic consistency via a distribution alignment training strategy. Extensive experiments demonstrate that CIAR achieves a 2.18x speed-up and reduces cloud requests by 70%, while preserving image quality compared to existing methods.