This work introduces RACER, a training-free closed-loop controller that continuously shrinks uncertain forecasts toward the last computed feature and derives a deterministic error bound for the shrinkage and empirically evaluates its validity and tightness across acceleration regimes.
Abstract
Training-free feature forecasting accelerates diffusion sampling by predicting features at skipped denoising steps. Recent work has mainly focused on designing stronger forecasters. Yet forecast error varies sharply across steps, and open-loop caches trust the forecast in full at every skipped step. This fixed trust is what breaks as acceleration turns aggressive. The missing question is not only how to forecast better, but when and how much to trust a forecast. We show that reliability can be observed from the cache itself. Two forecasts agree where the feature trajectory is smooth, and they diverge where prediction turns hard. Their disagreement is a cheap runtime signal, and it costs no extra denoiser evaluation. Based on this signal, we introduce RACER, a training-free closed-loop controller with two responses. It continuously shrinks uncertain forecasts toward the last computed feature. At the riskiest steps, RACER refreshes the feature and repays the added evaluation by skipping a later scheduled one. We derive a deterministic error bound for the shrinkage and empirically evaluate its validity and tightness across acceleration regimes. At the same number of denoiser evaluations, RACER improves the strongest open-loop baseline across SD3.5-Large, FLUX.1-dev, Wan2.1-14B, and HunyuanVideo on DrawBench, VBench, and COCO. On SD3.5, we further show that RACER samples faster at equal quality. RACER generalizes across forecasting designs as well. For example, it recovers much of the quality lost on a Taylor base. These results show that reliable diffusion acceleration also depends on how forecasts are used. Code is available at https://github.com/LiZaiyuan0619/RACER
This work proposes Hybrid-Basis Feature Forecasting (HybridFF), a training-free, plug-and-play framework for accelerating diffusion sampling that demonstrates a favorable speedup--quality trade-off over representative single-basis forecasters and caching baselines.
K. Cheng, Yuan-Yuan Cheng, Yu-Fang Jin et al.· 0 citations
Many scientific forecasting tasks require updating a distribution over future trajectories as new observations arrive. Conventional diffusion and flow models generate each forecast from Gaussian noise, often at the cost of many sampling steps. Warm-start methods reuse earlier predictions to reduce this cost, but their...
Yi-Nan Huang, Shitij Govil, Bo Dai et al.· 0 citations
Recent probabilistic weather forecasters train stochastic predictors with the continuous ranked probability score (CRPS) to generate each ensemble member in a single forward pass. These models learn the predictive distribution from the forecast context alone, which becomes difficult at longer forecast horizons where un...
Joonhyeong Park, G. Nam, Hyungi Lee et al.· 1 citation
Pretrained time-series foundation models (TSFMs) are evaluated as forecasters of future values, yet for sparse series many decisions depend only on which future periods contain activity. Standard benchmarks do not assess this. On five sparse datasets, we rank positions within forecast windows that contain both events a...
Daniel Schoess, F. von Wangenheim· arXiv.org· 0 citations
The results support on-policy self-distillation as an efficient and analyzable approach to diffusion post-training by converting image-level reward guidance into explicit and continually refreshed intermediate supervision, thereby opening a path toward more efficient and diagnosable alignment.
Weina Zhou, Xiongwei Zhu, Ling-Dong Kong et al.· 9 citations
The main finding is that a frozen parent's recursive trajectory is easier to fit than the observed future with lightweight parallel exits, and a correctable residual projection along a train-selected periodic history direction is found.