BCMT: Blockwise Causal Memory Transformer

Researchers introduced BCMT (Blockwise Causal Memory Transformer), a new architecture for long-context language modeling that decouples local token interactions from global context propagation, achieving validation performance comparable to Dense Transformers on contexts up to 1024 tokens while significantly improving training throughput and reducing memory consumption. The architecture applies dense causal self-attention within local blocks and uses an exponential causal memory of block summaries to propagate long-range context, avoiding explicit global attention and learned memory states.

arXiv:2608.13578v1 Announce Type: new Abstract: 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.