# SchemaMem: Schema-Indexed Recurrent Memory for Delayed State Retrieval

arXiv: https://arxiv.org/abs/2609.33436 · HTML: https://mlsanity.com/paper/2609.33436/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 14 references that are in the map.
- First posted on arXiv 27 Sep 2026.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mamba: Linear-Time Sequence Modeling with Selective State Spaces](https://mlsanity.com/paper/2312.00752/) (2023)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Neural Turing Machines](https://mlsanity.com/paper/1410.5401/) (2014)
- [Gated Delta Networks: Improving Mamba2 with Delta Rule](https://mlsanity.com/paper/2412.06464/) (2024)
- [Parallelizing Linear Transformers with the Delta Rule over Sequence Length](https://mlsanity.com/paper/2406.06484/) (2024)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [Block-Recurrent Transformers](https://mlsanity.com/paper/2203.07852/) (2022)
- [Augmenting Self-attention with Persistent Memory](https://mlsanity.com/paper/1907.01470/) (2019)
- [Mamba-3: Improved Sequence Modeling using State Space Principles](https://mlsanity.com/paper/2603.15569/) (2026)
- [MemMamba: Rethinking Memory Patterns in State Space Model](https://mlsanity.com/paper/2510.03279/) (2025)

## Abstract (arXiv)

Attention provides direct access to past representations, but retaining an ever-growing history is costly. Recurrent models bound persistent state, yet must preserve selected information while processing subsequent inputs. We introduce SchemaMem, an attention-based recurrent memory architecture combining chunk-local attention with a persistent, schema-indexed phase state. Learned schema embeddings provide a shared representational reference for reading and writing. Reads use the current state, whereas writes use the layer input and static schema embeddings, excluding direct feedback from that layer's own state. Chunk-boundary commits aggregate bounded phase increments through forward computation. The same parameters also support full-history attention training before and during recurrent training. We studied selective updates, preservation, and delayed retrieval in a controlled address--value task, comparing three-layer models with approximately matched parameter counts and persistent-state dimensions. Across nine address/value settings and three training seeds, SchemaMem has higher mean written-value retention at four times the maximum training delay than both baselines, which are trained toward a higher in-range accuracy target. Updated-value recovery favors SchemaMem in all nine settings against Mamba-3 and seven against Gated DeltaNet. Defaults consistently favor Gated DeltaNet over SchemaMem at that delay, and SchemaMem requires substantially more optimization steps. These results identify a promising retention--optimization trade-off in schema-indexed recurrence.