Post-Boundary Bridge (PBB), which preserves causal attention within blocks and adds direct connections across their boundaries, shows that targeted boundary exchange can preserve model quality while enabling faster, more memory-efficient local attention between global layers.
Abstract
Hybrid Transformers reduce the cost of long-context modeling by combining local attention with periodic full-attention layers. When global communication is already available, however, the best use of local computation remains unclear. We introduce Post-Boundary Bridge (PBB), which preserves causal attention within blocks and adds direct connections across their boundaries. Rather than extending the range of information relayed through successive local layers, PBB prioritizes within-block modeling and nearby exchange, leaving long-range communication to full-attention layers. Across dense and mixture-of-experts models with 205 million to 2.07 billion stored parameters, PBB hybrids retain near-Full perplexity and competitive performance on standard downstream benchmarks while improving controlled source retrieval. At 205 million parameters, PBB also matches a hybrid using sliding-window attention (SWA) in perplexity and achieves higher source-retrieval accuracy. The same boundary-aligned structure enables Flash-PBB, an exact decoding implementation that updates its key-value cache without relocating retained entries. Compared with Flash-SWA, Flash-PBB delivers 1.82x decode attention-core throughput with half the allocated local key-value cache. These results show that targeted boundary exchange can preserve model quality while enabling faster, more memory-efficient local attention between global layers.
Transformers achieve strong performance across modalities but are bottlenecked by the quadratic cost of attention. Sparse attention can reduce this cost, but effective sparsity must preserve useful long-range communication and map well to GPU hardware. We introduce INTRA--Interleaved Non-contiguous Token spaRse Attenti...
Yuxuan Xia, Wenbo Lu, Shao-Yi Zheng et al.· 0 citations
On an 80B-A3B MoE model, HySparse2 outperforms HySparse and Hybrid SWA on long-context retrieval and multi-turn agentic tasks, while substantially reducing prefill computation and KV-cache storage.
Hybrid architectures combining linear sequence models with softmax attention provide an effective balance between efficient long-context modeling and precise token retrieval. Existing designs such as Native Hybrid Attention (NHA) combine compressed long-term states with sliding-window attention, but their exact attenti...
Rui-Jie Li, Jia-Xi Hu, Shi-Yu Wang et al.· 0 citations
Hybrid language models can improve capability as well as efficiency, raising the question of how architectural complementarity becomes learned computation. We examine the established induction roles of Carrying predecessor information, Matching a source by content, and Copying its value. How are these position-sensitiv...
Ke Cheng, Xin Xu, Yi-Xiao Chen et al.· 0 citations
Semantic-Geometric Decoupled Routing is proposed, a training-free block routing framework that shifts semantic aggregation to the pre-RoPE space and reconstructs geometric bias with an offline structural prior and relative block distances and yields an explicit closed-form block routing score without token-level search...
Transformer compression often couples two distinct quantities: retained attention capacity and the number of sequential depths at which that capacity is executed. We study whether useful attention functions in a hierarchical vision transformer are locally mobile across depth. Using SegFormer-B5 for human segmentation,...
A. Druzhinin· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduNov 17, 2026
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026