The paper proposes Under-Cali, an uncertainty-driven dual-expert calibration framework, to achieve stable and efficient online forecasting for irregularly sampled multivariate time series.

The paper argues that long context windows are necessary for time series forecasting not just to capture long-range dependencies, but primarily to reduce uncertainty about the underlying data-generati…

The paper proposes a novel nonparametric mutual information estimator to robustly quantify dependence between heterogeneous temporal data, specifically continuous time series and discrete event sequen…

FreqLite introduces an ultra-lightweight, frequency-decomposed linear model that significantly outperforms complex transformers on long-term time-series forecasting while drastically reducing computat…

The paper proposes INTARG, an informed and selective adversarial attack framework for time-series forecasting that significantly increases prediction error by targeting only the most vulnerable time s…

ChronosAD introduces a novel architecture that uses time series foundation models and a custom Temporal Block to achieve robust and highly accurate anomaly detection across diverse domains.

The paper proposes VLBM, a latent basis modeling framework, to achieve state-of-the-art robustness in multivariate time series forecasting, particularly when facing rare but high-impact out-of-distrib…

The paper introduces TimeSage-MT, a comprehensive multi-turn benchmark designed to rigorously test an LLM agent's ability to perform complex, evolving time series analysis, revealing critical gaps in…

The paper introduces BlockGen, a blockwise sequence model, to investigate the performance of uniform-state versus masked diffusion models when generating sequences block-by-block, showing that the per…

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

This paper proposes Supervised Memory Training (SMT), a method for training nonlinear RNNs that sidesteps recurrent credit propagation entirely.

The paper introduces STEP, a self-supervised method that learns interpretable, structured embeddings for progressive time series, allowing the state progression and active mode to be read out using po…

The paper proposes SimSD, a plug-and-play speculative decoding algorithm that adapts diffusion language models (dLLMs) to achieve fast, token-level acceleration by restoring causal masking capabilitie…

SHARP proposes a novel sleep-based hierarchical replay framework to efficiently learn long-range non-stationary temporal patterns in streaming data, achieving improved context retention and predictive…

The paper introduces EvoXXLTraffic, an ultra-large, sensor-evolving dataset that simulates real-world road network growth, demonstrating that existing state-of-the-art traffic forecasting models fail…

The paper demonstrates that replacing standard pointwise losses (like MSE) with multi-quantile regression significantly improves precipitation nowcasting accuracy and provides valuable risk estimates…

The paper identifies a universal, statistically predictable distribution (Mandelbrot) governing LLM outputs, enabling a highly efficient, model-agnostic scoring primitive for provenance and quality as…

The paper proposes TimeGuard, a novel channel-wise pool training defense, to significantly improve the robustness of time series forecasting against backdoor attacks by addressing signal dilution and…

MORPHOS is a novel autoregressive framework that generates dynamic 3D assets (like meshes and radiance fields) from videos by using a unified 4D representation to ensure temporal consistency and handl…