SACQ introduces a structured prediction head for long‑horizon time‑series forecasting that replaces the traditional flatten readout. It uses a two‑stage decoding process: a coarse patch‑grid scaffold is first generated, then each future position is refined via cross‑attention over historical memory, with a learned gate merging the corrections. A batch‑adaptive scaled log‑cosh loss further stabilizes training under long horizons and noisy labels, leading to superior MSE/MAE performance across multiple backbones with minimal overhead.
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.
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:2610.10323v1 Announce Type: new Abstract: Short-horizon realized volatility forecasting requires the integration of market information that evolves at incompatible temporal resolutions, from se...
arXiv:2606. 08601v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated impressive potential for time series forecasting.
arXiv:2607. 00197v1 Announce Type: new Abstract: Long-horizon multivariate time series forecasting (LTSF) remains challenging due to non-stationarity, regime shifts, and error accumulation.
The paper introduces a hybrid attention model that learns a unified time‑aware patch representation for irregular multivariate time series (IMTS) forecasting. It employs a time‑aware patch encoding to embed variable‑length intra‑patch timestamps, a time bias attention mechanism to adjust for temporal misalignment and asynchronous cross‑channel dependencies, and a hybrid causal mask on a decoder‑only Transformer to balance historical context with autoregressive forecasting. The authors also curate VersaTSA, a 30 B‑observation dataset preserving native sampling sparsity, and demonstrate state‑of‑the‑art zero‑shot performance on three IMTS benchmarks while remaining competitive on regular MTS tasks.
arXiv:2608. 15062v1 Announce Type: cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency.
The paper introduces Gated Recurrent Transformers, a depth‑sharing architecture that brackets a single shared core with fixed prelude and coda blocks and uses a lightweight projection and element‑wise update gate to modulate recurrent updates. This design allows functional specialization across recurrences while reducing memory footprint. Experiments show that, under equal FLOPs or parameter budgets, the recurrent model matches or surpasses deeper GPT‑2 Small baselines, achieving similar or better accuracy with fewer parameters and lower peak decoding memory.
Dual-Context Analog Retrieval for Time Series Forecasting (DuoTS) introduces a two-stage forecasting approach that first generates a base forecast and then refines it patch by patch. Each refinement step fuses a current context, which focuses on recent tokens, with a detail context that incorporates retrieved analogs and their subsequent trajectories. Experiments on real-world datasets demonstrate that DuoTS achieves state‑of‑the‑art performance, and ablation studies confirm the importance of both contexts and the refinement mechanism.
arXiv:2608.15062v3 Announce Type: replace-cross Abstract: Scaling transformer language models creates an inherent tension between expressivity and memory efficiency. While unique weights across layer...
The paper introduces LoopCD, a training‑free contrastive decoding framework that improves token selection in Loop‑Transformer models by comparing the final prediction with earlier recurrent passes. LoopCD operates either in logit space (LoopCD‑Logits) with a single extra output pass or in hidden‑state space (LoopCD‑Hidden) with no output overhead. Across multiple looped Transformer families, LoopCD yields significant performance gains—raising pass@1 scores on tasks such as AIME 2024 and HumanEval—while enabling a reduction in the number of recurrent loops and a corresponding decrease in inference FLOPs.
arXiv:2607. 09537v1 Announce Type: new Abstract: Time series forecasting requires models to capture diverse, often mutually exclusive, temporal dynamics, from smooth trend continuation to nonstationary drift and strict phase-aligned recurrence.