# BCMT: Blockwise Causal Memory Transformer

arXiv: https://arxiv.org/abs/2608.13578 · HTML: https://mlsanity.com/paper/2608.13578/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 6 Jul 2026.

## Builds on (most cited first, 21 of 21)

- [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)
- [Longformer: The Long-Document Transformer](https://mlsanity.com/paper/2004.05150/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [Rethinking Attention with Performers](https://mlsanity.com/paper/2009.14794/) (2020)
- [Linformer: Self-Attention with Linear Complexity](https://mlsanity.com/paper/2006.04768/) (2020)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Compressive Transformers for Long-Range Sequence Modelling](https://mlsanity.com/paper/1911.05507/) (2019)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [MetaFormer Is Actually What You Need for Vision](https://mlsanity.com/paper/2111.11418/) (2021)
- [LongNet: Scaling Transformers to 1,000,000,000 Tokens](https://mlsanity.com/paper/2307.02486/) (2023)
- [Recurrent Memory Transformer](https://mlsanity.com/paper/2207.06881/) (2022)
- [Funnel-Transformer: Filtering out Sequential Redundancy for Efficient Language Processing](https://mlsanity.com/paper/2006.03236/) (2020)
- [Blockwise Self-Attention for Long Document Understanding](https://mlsanity.com/paper/1911.02972/) (2019)
- [Token Pooling in Vision Transformers](https://mlsanity.com/paper/2110.03860/) (2021)
- [Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents](https://mlsanity.com/paper/2507.22925/) (2025)
- [Hierarchical Autoregressive Transformers: Combining Byte- and Word-Level Processing for Robust, Adaptable Language Models](https://mlsanity.com/paper/2501.10322/) (2025)
- [Pretraining with hierarchical memories: separating long-tail and common knowledge](https://mlsanity.com/paper/2510.02375/) (2025)
- [Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts](https://mlsanity.com/paper/2506.05229/) (2025)
- [Hierarchical Resolution Transformers: A Wavelet-Inspired Architecture for Multi-Scale Language Understanding](https://mlsanity.com/paper/2509.20581/) (2025)

## Abstract (arXiv)

Transformer architectures rely on dense self-attention to model long-range dependencies, but this mechanism exhibits quadratic complexity with respect to sequence length. We introduce BCMT (Blockwise Causal Memory Transformer), an architecture for long-context language modeling that decouples local token interactions from global context propagation. Dense causal self-attention is applied independently within local blocks, while each block produces an adaptive summary aggregated through an exponential causal memory. This memory is subsequently injected back into the token representations, enabling efficient propagation of long-range contextual information without relying on explicit global attention. Unlike standard Transformers and recurrent memory architectures, BCMT maintains neither dense interactions between distant tokens nor learned memory states. Its memory mechanism is fully parallelizable and remains compatible with standard implementations of dense self-attention. Experiments on language modeling with context lengths of up to 1024 tokens show that BCMT achieves validation performance comparable to that of Dense Transformers while significantly improving training throughput and reducing memory consumption. An ablation study further confirms that these improvements arise from the proposed memory mechanism. These results demonstrate that an exponential causal memory constructed from block summaries provides an effective alternative to dense global attention mechanisms for long-context language modeling.