arXiv Machine Learning
Parameter-Efficient Temporal Domain Generalization
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Machine Learning
Aug 10
Beyond Myopic World Models: Long-Horizon End-to-End Training for Direct Future Prediction
arXiv:2608. 07420v1 Announce Type: new Abstract: World models are expected to support imagination over extended temporal horizons, yet most are still trained through local few-step prediction objectives and deployed by recursively rolling out their own predictions.
arXiv Machine Learning
Oct 21
ORBIT: Autoregressive Time Series Generation via Next Frequency-Band Prediction
arXiv:2610.27000v1 Announce Type: new Abstract: Deep generative models provide an effective modern solution to alleviating the problem of data scarcity by synthesizing realistic time series. However,...
arXiv AI
Oct 9
Timer-M1: A Multivariate Time Series Foundation Model via Learning Primitives
Timer‑M1 is a pretrained multivariate time‑series foundation model that learns with primitives for zero‑shot forecasting. It uses a primitive‑based data synthesis and pretraining pipeline to generate series with shared temporal and relational patterns, assembling them into multivariate samples with distinct channel roles. The model employs gated two‑dimensional Transformer blocks that dynamically allocate cross‑variate attention, achieving top performance on several large‑scale forecasting benchmarks.
arXiv AI
1d ago
AdaMamba: Adaptive Frequency-Gated Mamba for Long-Term Time Series Forecasting
AdaMamba introduces an adaptive frequency-gated Mamba architecture for long‑term time series forecasting. The model integrates an interaction learning module that captures cross‑variable dependencies and multi‑scale context, and an adaptive frequency‑gated state space module that generates context‑dependent frequency bases and unifies temporal forgetting into a single time‑frequency gate. Experiments on seven public benchmarks and four domain‑specific datasets show that AdaMamba consistently outperforms state‑of‑the‑art baselines while remaining computationally efficient.
arXiv Machine Learning
Oct 12
HART: Hybrid Attention-RWKV Time series Foundation Model
The paper introduces HART, a Hybrid Attention-RWKV Time-series Foundation Model that alternates attention and RWKV blocks to improve long-horizon forecasting. It identifies a problem in RWKV-7 called Placeholder Idling Decay, where repeated state transitions degrade historical information during non-autoregressive multi-step forecasting. Experiments on GIFT-Eval and TIME-Benchmark show that HART outperforms pure RWKV on medium and long horizons while matching short-horizon performance, and achieves comparable long-horizon MASE to a much larger Transformer with only 36 M parameters.
arXiv Machine Learning
Aug 7
Kastor: An efficient fine-tuning strategy for generative emulation of PDE simulations
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.