Almanac
technique

triplet-block layout

techniqueactiveprovisionaltriplet-block-layout-2ae36a88·1 events·first seen 22d ago

Aliases: triplet-block layout

Co-occurring entities

More like this (12)

Recent events (1)

6arXiv · cs.CL·22d ago·source ↗

Triplet-Block Diffusion RWKV: Unifying Linear-Time Causal Models with Bidirectional Discrete Diffusion

The paper introduces B³D-RWKV, a 7.2B-parameter language model that combines RWKV's O(L) linear-time inference with parallel bidirectional discrete diffusion via a triplet-block layout. This architecture resolves the fundamental tension between causal (unidirectional) and diffusion (bidirectional) attention requirements. On an 8-task evaluation suite, B³D-RWKV-7.2B achieves comparable accuracy to existing models while delivering an average 1.6× decoding throughput speedup over baselines.