Tag
该论文提出 Control-TS，通过残差控制将预测分位数作为分布控制信号引入预训练扩散预测模型，并提出 CLPS 指标评估生成未来轨迹的下游预测效用，在八个基准上一致提升 CRPS 表现。
QuantFlow introduces a federated Mamba-based foundation model for time-series forecasting that combines inverted sequence embedding, bidirectional state-space decoders, and quantile regression to achieve strong results on benchmarks while preserving data privacy.
This paper presents a sparse Gaussian process framework for quantile regression that uses a Laplace approximation for posterior inference and variance-based mechanisms for adaptive inducing-input placement and data acquisition.
Introduces Q-srdrn, a multi-quantile super-resolution network using pinball loss to improve extreme precipitation downscaling, achieving dramatic detection rate gains for heavy rainfall events while maintaining overall accuracy.
This paper introduces RQIQN, a robust quantile-based method for distributional reinforcement learning that uses Wasserstein geometry regularization to prevent distribution degeneration and improve performance in risk-sensitive tasks.
Amazon and Stanford researchers propose Quantile Token Regression, inserting dedicated quantile tokens into LLM inputs to predict full probability distributions, achieving ~4 point MAPE reduction and 2× narrower intervals on Airbnb and Stack Overflow benchmarks.