arXiv:2603. 01959v2 Announce Type: replace Abstract: State-Space Models (SSMs) have recently been shown to achieve strong empirical performance on a variety of long-range sequence modeling tasks while remaining efficient and highly-parallelizable.
By Mehran Shakerinava, Behnoush Khavari, Siamak Ravanbakhsh, Sarath Chandar
The paper investigates how neural networks, particularly Transformers and recurrent models, learn to track group elements by predicting their running product. It finds that Transformers tend to recover quotient classes and that their accuracy can be predicted by the reciprocal of class size, while recurrent networks can capture both normal and non‑normal right‑coset partitions. The study links partial accuracy, learning stages, and internal state representations to the subgroup cosets the models learn to track.
By Zhiyu Zhang, Yupeng Li
arXiv:2609.28273v1 Announce Type: cross
Abstract: State tracking from sequential observations can require both retaining information and updating it by composing observed operations. We extend Mamba-...
By Hiroki Fujii, Masaki Yamakita
The paper introduces CHASE, a cache‑hole‑adapted skip‑exit mechanism for looped state‑space language models, specifically Looped Mamba and Looped Hybrid Mamba‑Transformer. It shows that looping these architectures improves performance on controlled reasoning tasks and remains competitive in pre‑training benchmarks while using fewer distinct parameters. The cache‑hole adaptation allows selective skipping of recurrent steps during inference, maintaining perplexity close to full computation and achieving significant speedups.
By Zhenxuan Yu, Takeshi Kojima, Yutaka Matsuo, Yusuke Iwasawa
arXiv:2607. 21000v1 Announce Type: new Abstract: Long-sequence memory tracking places two opposing demands on a recurrent state: near-lossless retention of stored bindings over long horizons, and active overwriting of stale ones.
By Hyuk Lim, Seunghyun Yoon
arXiv:2608. 19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps.
By Xinyi Fan, Miri Liu, Ruozhen Yang, Siru Ouyang, Jiawei Han