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

The paper introduces QuITE, a plug-and-play embedding module that uses learnable query tokens to effectively embed irregular multivariate time series data into latent representations compatible with e…

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…

The paper introduces NaRA, a noise-aware LoRA technique that dynamically adapts fine-tuning parameters based on the noise level during diffusion, significantly improving the performance of Diffusion L…

The paper introduces an LLM-agent framework to solve the 'last-mile forecasting' problem, bridging the gap between raw statistical predictions and business-ready forecasts by incorporating weakly stru…

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

HARP introduces a novel, adaptive, learnable orthogonal processor that significantly improves the robustness and accuracy of extreme low-bit LLM quantization compared to fixed methods.

This paper demonstrates that Large Language Models (LLMs) can serve as accurate and selective surrogates for costly GPU kernel performance measurements, significantly expanding the search space for op…

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…

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 proposes a decision-aware quadratic replacement for the ReLU activation function, enabling low-degree, calibration-lossless polynomial approximations for neural network inference under Fully…

The paper formalizes LLM degradation during long generation as 'cognitive fatigue' and introduces the Fatigue Index (FI), a measurable, model-agnostic diagnostic tool for real-time monitoring.

AdaKoop introduces an efficient streaming algorithm that models complex nonlinear dynamics from nonstationary data streams by leveraging the Koopman operator theory, achieving state-of-the-art accurac…

FLARE is a systematic conversion framework that enables a single checkpoint to support both autoregressive (AR) and diffusion-style parallel decoding for hybrid-attention large language models, achiev…

BudgetDraft introduces an acceptance-aware multi-view training method that trains a sparse-KV speculative decoder to maintain high acceptance rates across varying context lengths and sparsity levels,…

The paper introduces Entropic Projection Alignment (EPA), a unified framework that estimates, explains, and improves model performance under distribution shift by aligning source and target distributi…

The paper introduces an adaptive reservoir computing framework that tailors Echo State Networks (ESNs) to specific evaluation scenarios, achieving a high score on the CTF-4-Science Lorenz benchmark fo…