The paper introduces Interdomain Attention (IA), a hybrid architecture that blends softmax attention with recurrent memory within a single layer, leveraging a kernel regression perspective to compress keys and values into a state‑space model (SSM) memory. IA reconstructs the attention matrix implicitly from memory states, preserving the computational efficiency of SSMs while achieving performance gains. Experiments on models ranging from 125 M to 1.3 B parameters show IA surpasses an S4D baseline at matched memory size, outperforms standard Transformers on perplexity and common‑sense reasoning, and matches or exceeds SSM‑based models on genomic downstream tasks.
By Naoki Kiyohara, Harrison Bo Hua Zhu, Riccardo El Hassanin, Zhuo Sun, Wenlong Chen, Samir Bhatt, Yingzhen Li
The paper introduces the Progressive Memory Transformer (PMT), a transformer variant that adds writable, window‑aligned memory to expose mid‑range representations alongside token and sequence‑level outputs. PMT is trained with a hierarchical learning framework that applies separate objectives at local, mid‑range, and global scales, encouraging the model to capture fine‑grained variation, window‑level motifs, and overall sequence agreement. Experiments on seven UCR/UEA/UCI classification datasets, a cue‑retention probe, and forecasting tasks show that PMT achieves strong low‑label classification performance, competitive multi‑horizon forecasting, and evidence that its memory states encode mid‑range motifs.
By Tord Sture Stangeland, Andreas K\"ohler, Steffen M{\ae}land, Ad\'in Ram\'ires Rivera
arXiv:2605. 11287v2 Announce Type: replace-cross Abstract: A persistent paradox in time-series forecasting is that structurally simple MLP and linear models often outperform high-capacity Transformers.
By Jevon Twitty, Vinh Pham, Nitiwith Rotchanarak, Viresh Pati, Yubin Kim, Shihao Yang, Jiecheng Lu
arXiv:2607. 02344v1 Announce Type: cross Abstract: Transformer architectures have shown strong potential in time series forecasting, where multi-head self-attention is widely used to capture temporal dependencies across historical timestamps.
By Dezheng Wang, Tong Chen, Wei Yuan, Congyan Chen, Shihua Li, Hongzhi Yin
arXiv:2610.19603v1 Announce Type: new
Abstract: Transformers have demonstrated strong performance in long-term time series forecasting (LTSF), yet modeling non-stationary temporal dependencies remain...
By Xinjie Lan, Yunbo Mei, Leheng Zhou, Hao Qi
TimeBraid is a family of unified models that combine pretrained language models with pretrained time‑series foundation models using interleaved global residual attention layers. The models inherit instruction following, reasoning, and continuous‑signal perception, fusing both modalities into a shared representation space for understanding and generation. The design focuses on aligning representation spaces, grounding language in temporal structure, balancing understanding with generation, and maintaining stable joint optimization, supported by 2.2 M curated series‑text pairs and 4.9 M instruction‑tuning samples. Across diverse benchmarks, TimeBraid competes with larger general‑purpose and task‑specific models.
By Xinyue Wang, Jiacheng Pang, Kun Zhou, Kexin Zhang, Defu Cao, Fan Feng, Faisal, Songyao Jin, Yan Liu, Biwei Huang
The paper introduces Higher-Order Modular Attention (HOMA), a new attention mechanism that combines standard pairwise self‑attention with an explicit triadic attention pathway. HOMA uses overlapping blocks, local windows, and a low‑rank projection to make triadic interactions tractable. Experiments on controlled PARITY and MATCH3 tasks, as well as TAPE benchmarks, show that HOMA matches or outperforms matched pairwise and purely triadic baselines, especially when dependencies extend beyond triadic order, and it often converges faster and uses parameters more efficiently.
By Shirin Amiraslani, Xin Gao
arXiv:2606. 04833v1 Announce Type: cross Abstract: Initially developed for natural language processing, Transformer architectures and attention mechanisms are now central to a wide range of deep learning models, including applications in time series forecasting.
By Balthazar Courvoisier, Tristan Cazenave
arXiv:2605. 27286v2 Announce Type: replace-cross Abstract: Time series foundation models (TSFMs) are transforming the forecasting paradigm through large-scale cross-domain pretraining.
By Yiding Liu, Yifan Hu, Hongjie Xia, Peiyuan Liu, Hongzhou Chen, Xilin Dai, Zewei Dong, Jiang-Ming Yang
arXiv:2606. 18587v1 Announce Type: cross Abstract: Decoder-only Transformers compute attention over the KV cache of preceding tokens.
By Zhiyuan Wang, Xuan Luo, Sirui Zeng, Xifeng Yan
arXiv:2511. 20577v5 Announce Type: replace Abstract: Real-world time series often exhibit strong non-stationarity, complex nonlinear dynamics, and behavior expressed across multiple temporal scales, from rapid local fluctuations to slow-evolving long-range trends.
By Sumit S Shevtekar, Chandresh K Maurya
arXiv:2606. 08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting.
By Peiliang Gong, Emadeldeen Eldele, Chenyu Liu, Ziyu Jia, Yi Ding, Xinliang Zhou, Lianchao Gu, Qi Zhu, Yang Liu, Daoqiang Zhang, Xiaoli Li