直觉引领：自回归图像生成中的置信度扩展

摘要

测试时缩放（TTS）在提升大型语言模型方面已展现出显著成效，然而其在基于下一令牌预测（NTP）的自回归（AR）图像生成中的应用仍鲜有探索。现有的视觉自回归（VAR）TTS方法，依赖于频繁的部分解码和外部奖励模型，由于中间解码结果固有的不完整性，并不适用于基于NTP的图像生成。为填补这一空白，我们提出了ScalingAR，这是首个专为基于NTP的AR图像生成设计的TTS框架，无需早期解码或辅助奖励。ScalingAR创新性地利用令牌熵作为视觉令牌生成的新信号，并在两个互补的缩放层级上运作：（i）轮廓层级，通过融合内在与条件信号，流式传输校准后的置信状态；（ii）策略层级，利用此状态自适应地终止低置信度轨迹，并动态调度指导以适应当前阶段的调节强度。在通用与组合基准上的实验表明，ScalingAR（1）在GenEval上使基础模型提升了12.5%，在TIIF-Bench上提升了15.2%；（2）高效地减少了62.0%的视觉令牌消耗，同时性能超越基线；（3）显著增强了鲁棒性，在挑战性场景下将性能下降减少了26.0%。

English

Test-time scaling (TTS) has demonstrated remarkable success in enhancing large language models, yet its application to next-token prediction (NTP) autoregressive (AR) image generation remains largely uncharted. Existing TTS approaches for visual AR (VAR), which rely on frequent partial decoding and external reward models, are ill-suited for NTP-based image generation due to the inherent incompleteness of intermediate decoding results. To bridge this gap, we introduce ScalingAR, the first TTS framework specifically designed for NTP-based AR image generation that eliminates the need for early decoding or auxiliary rewards. ScalingAR leverages token entropy as a novel signal in visual token generation and operates at two complementary scaling levels: (i) Profile Level, which streams a calibrated confidence state by fusing intrinsic and conditional signals; and (ii) Policy Level, which utilizes this state to adaptively terminate low-confidence trajectories and dynamically schedule guidance for phase-appropriate conditioning strength. Experiments on both general and compositional benchmarks show that ScalingAR (1) improves base models by 12.5% on GenEval and 15.2% on TIIF-Bench, (2) efficiently reduces visual token consumption by 62.0% while outperforming baselines, and (3) successfully enhances robustness, mitigating performance drops by 26.0% in challenging scenarios.

直觉引领：自回归图像生成中的置信度扩展

Go with Your Gut: Scaling Confidence for Autoregressive Image Generation

摘要

Support