AI RESEARCH
Parallel Decoder Transformer: Planner-Seeded Latent Coordination for Synchronized Parallel Decoding
arXiv CS.CL
•
ArXi:2512.10054v2 Announce Type: replace-cross Autoregressive language models can often identify parallel subproblems, but standard decoding exposes only a single left-to-right output interface. External orchestration methods can launch multiple prompts concurrently, yet they provide no model-internal state through which those generations can synchronize, resolve ownership, or wait for missing information.