arXiv:2510. 23636v4 Announce Type: replace-cross Abstract: Flight delay prediction has become a key focus in air traffic management (ATM), as delays reflect inefficiencies in the system.
M3-Former is a multimodal transformer framework that uses large language models to encode vessel static attributes and navigational intent as semantic priors for long‑term trajectory prediction. It builds a unified multimodal representation space, aligns static semantic information with dynamic trajectory features via self‑attention, and employs a dual‑granularity Mixture‑of‑Experts architecture to capture both global route planning and fine‑grained maneuvering behaviors. A Steering‑Weighted Cross‑Entropy loss further improves accuracy on sparse turning events, and experiments on a Danish AIS dataset show consistent improvements over state‑of‑the‑art baselines, reducing ADE and FDE by up to 5.1% in 4‑hour predictions.
Aurora‑X is a billion‑parameter time‑series foundation model designed for extreme forecasting tasks. It employs a progressive curriculum that starts with channel‑independent pretraining, then adds cross‑variable dependencies, variable context and horizon lengths, and optional future covariates during mid‑training. A variable‑resolution post‑training stage allows adjustable temporal spans per token at inference, while a pattern‑guided mixture‑of‑experts expands capacity through sparse activation and expert specialization. An implicit quantile network head predicts arbitrary quantiles, enhancing probabilistic forecasting flexibility. Experiments on GIFT‑Eval, TIME, FEV‑Bench, TFB, and DAG‑Bench show state‑of‑the‑art performance against both pretrained TSFMs and task‑specific supervised models.
arXiv:2508. 07195v2 Announce Type: replace-cross Abstract: Recent advances have demonstrated that Large Language Models (LLMs) can be effectively adapted for time series forecasting, revealing strong potential beyond natural language tasks.
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution. However, because this supervision is generated via uncontrolled sampling, it provides no diagnostic insight into the model's specific errors or corrective guidance for its individual failure patterns.
arXiv:2609.15344v1 Announce Type: new Abstract: We study the adaptation of pretrained language models to univariate time-series forecasting through a parameter-efficient transfer learning framework,...
arXiv:2606. 08633v1 Announce Type: new Abstract: Long-horizon maritime trajectory prediction is important for shipping management, logistics planning, and maritime risk analysis, yet month-level forecasting remains insufficiently studied.
arXiv:2606. 18844v1 Announce Type: new Abstract: Self-distillation improves reasoning in large language models by using the model's own rollouts as training signal, typically through implicit logit-level alignment that minimizes KL divergence toward a privileged target distribution.
arXiv:2606. 15240v2 Announce Type: replace Abstract: Accurate vessel trajectory forecasting is essential for maritime situational awareness, navigation safety, traffic management, and autonomous navigation.
The paper introduces TRACE-CRC, a trajectory‑adaptive conformal risk control method for multi‑step channel state information (CSI) prediction. It builds Frobenius‑norm uncertainty balls around predicted CSI matrices and controls the risk that any future frame is uncovered, using future‑step‑dependent error profiling, trajectory difficulty stratification, and learn‑then‑test risk control. Experiments show that TRACE‑CRC delivers reliable trajectory‑level coverage with smaller uncertainty balls than conservative multi‑step corrections and avoids undercoverage seen in stepwise and adaptive baselines.
Orthogonal JEPA introduces a latent world‑modeling framework that factorizes predictive states into orthogonal components. By learning basis matrices and dedicated prediction branches, the method reduces redundancy and improves gradient signals for less dominant predictive structures. The factorized states can be synthesized into complete latent representations for downstream tasks such as decoding, planning, or autoregressive rollout, and are evaluated across vision, biology, health, control, and molecular dynamics domains.