Tag
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.