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.
arXiv:2606. 09861v1 Announce Type: cross Abstract: While Next-Token Prediction (NTP) has unified LLM pretraining, its adaptation to unbounded, continuous time series (TS) remains open.
arXiv:2606. 00732v1 Announce Type: new Abstract: Learning long-range non-stationary temporal patterns remains a core challenge for modern sequence models, particularly in strict streaming settings.
arXiv:2604. 01577v3 Announce Type: replace-cross Abstract: We study out of distribution generalization in streaming tasks where models are trained on short sequences but must operate over much longer, unknown horizons under bounded memory.
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.
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.
arXiv:2606. 18587v1 Announce Type: cross Abstract: Decoder-only Transformers compute attention over the KV cache of preceding tokens.
arXiv:2606. 12364v1 Announce Type: new Abstract: Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost.
InfoMamba is an attention‑free hybrid model that combines a minimal‑bandwidth global interface with a selective recurrent stream. The architecture replaces token‑level self‑attention with a concept bottleneck linear filtering layer and integrates it via an information‑maximizing fusion (IMF) that injects global context into the state‑space dynamics. Experiments across classification, dense prediction, and non‑vision tasks show that InfoMamba outperforms strong Transformer and SSM baselines while maintaining near‑linear scaling and competitive accuracy‑efficiency trade‑offs.
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.
arXiv:2606. 06479v1 Announce Type: new Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations.
arXiv:2606. 08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting.
arXiv:2606. 10678v1 Announce Type: new Abstract: Transformer-based models have emerged as leading paradigms in time-series forecasting in recent years, employing self-attention mechanisms to capture long-range dependencies.