arxiv
PublishedJune 26, 2026 at 4:00 AM
—neutral
Learning State-Tracking from Code Using Linear RNNs
Publisher summary· verbatim
arXiv:2602.14814v3 Announce Type: replace-cross Abstract: Over the last years, state-tracking tasks, particularly permutation composition, have become a testbed to understand the limits of sequence models architectures like Transformers and RNNs (linear and non-linear). However, these are often sequ
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivBringing Value Models Back: Generative Critics for Value Modeling in LLM Reinforcement Learning27marxivSubagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks27marxivDistribution-Consistent Inference for Dynamic Sparse Mixture-of-Experts27marxivIn RAG We Trust? Measuring Robustness of Retrieval-Augmented Generation Under Document Poisoning27mThe Bubble Brief
WEEKLYRead sequence models insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗