The paper introduces Recursive Quadrature Filters (RQFs), complex‑valued temporal filters that act as band‑pass filters within diagonal state‑space models. By making each layer’s bottom‑up input prospective through a parameter‑free two‑tap update, the authors mitigate depth‑dependent gradient attenuation in deep continuous‑time recurrent networks. Experiments on RQFs, S5, and ORGaNICs show that prospective variants match or surpass non‑prospective controls, achieving high accuracy on raw‑audio Speech Commands and the Path‑X task with few parameters.
By Shivang Rawat, Mirko Morello, Flaviano Morone, David J. Heeger
arXiv:2606. 06479v1 Announce Type: new Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations.
By Akarsh Kumar, Phillip Isola
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.
By Jayanta Dey, Shikhar Srivastava, Itamar Lerner, Christopher Kanan, Dhireesha Kudithipudi
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: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.
By Xinyi Li, Zaishuo Xia, Chenjie Hao, Yubei Chen
Fast Weight Attention for Continual Learning introduces recurrent fast‑weight memories and selective state‑space models that compress expanding context into a fixed‑size recurrent state, enabling an online learning rule for state transitions. The paper derives normalized first‑order updates for squared‑error regression and negative inner‑product objectives, presenting several variants (Falcon‑1, Falcon‑2, Falcon‑3 and their inner‑product counterparts) with recurrent, masked‑parallel, and chunk‑parallel implementations. These methods demonstrate competitive performance in language modeling and improved length extrapolation on variable‑digit addition tasks.
By Yifan Zhang, Steve Ta, Jasper Zhang, Jichen Feng, Shuzhen Li, Yongxin Zhang, Yifeng Liu, Huizhuo Yuan, Mengdi Wang, Quanquan Gu, Andrew Chi-Chih Yao
The paper investigates how the sequence of hidden-state optimization affects feature learning in local-learning models, specifically predictive coding networks (PCNs). It introduces a boundary-first inference schedule that first aligns hidden states at chunk boundaries before refining representations within each chunk. Experiments on CIFAR-10 show that this approach improves accuracy by 9.77% over standard PCNs and 5.51% under a different parametrization, with diagnostics indicating stronger feature learning.
By Xueyuan Li, Danilo Vasconcellos Vargas
The paper introduces Decision Titan, a variant of the Decision Transformer that incorporates Test‑Time Training (TTT) layers to store episodic memories in network parameters. It evaluates this architecture on the X‑Maze environment, showing that Decision Titan can learn long‑term dependencies up to 20 times longer than its context window and generalise to sequences 1.7 times longer than the training data. The study also finds that temporal generalisation depends on the choice of time embeddings and that the ability to learn long‑term dependencies hinges on how relevant information is encoded.
By Jude Waide, Robert Lieck
arXiv:2606. 24969v1 Announce Type: new Abstract: While the quadratic sequence-length bottleneck of transformers has fueled a resurgence in recurrent models, effectively capturing complex dynamics requires architectures that balance efficient training with highly expressive latent states.
By Klaus Schertler, Xiomara Runge, Andrea Ceni, David Kappel, Claudio Gallicchio
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.
By Shota Takashiro, Masanori Koyama, Takeru Miyato, Yusuke Iwasawa, Yutaka Matsuo, Kohei Hayashi
The paper introduces the AGI Maze Prediction Datasets and Benchmark, a lightweight, procedurally generated grid‑world testbed for evaluating predictive models, particularly Transformers, on tasks such as per‑step transition prediction, fixed‑horizon state prediction, and sequential textual‑observation prediction. It compares byte‑level Transformer baselines with two memory‑augmented architectures, showing that a pseudo‑video spatial‑memory Transformer achieves perfect validation accuracy on selected tasks and improves sequential text‑trace prediction, while a generic auxiliary latent‑memory Transformer does not consistently help. The study highlights that structured, task‑aligned working memory can be more effective than merely increasing latent capacity, and positions the benchmark as a compact setting for testing architectures that couple textual interfaces to learned structured state.
By Alexey Potapov
Local learning methods offer an alternative to end-to-end backpropagation, but their unstructured local objectives can produce weak feature learning in deep networks. We study whether the order of hid...