paper-with-me

Papers

Parallel Decoder Transformer: Planner-Seeded Latent Coordination for Synchronized Parallel Decoding

2025-12-10 · Logan Robbins arxiv

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. We present the Parallel Decoder Transformer (PDT), a frozen-trunk architecture that augments a decoder with a planner-seeded latent workspace and a synchronized multi-stream output protocol. Before any stream emits tokens, a mandatory prompt-time planner predicts fixed latent plan slots and projects them as snapshot 0 on an embeddings-only Dynamic Notes Bus. During decoding, each stream reads the visible notes window through Speculative Note Conditioning (SNC), emits provisional token blocks and latent summaries, and advances only when agreement logic determines that the current shared state is sufficient for continued parallel generation. Coverage heads track plan-item ownership, while rollback handles incoherent or premature commits. PDT therefore shifts parallel task decomposition from an external prompting strategy to a model-internal coordination mechanism over the output interface of a frozen language model.

📄 PDF Abstract BibTeX arXiv:2512.10054

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ColaVLA: Leveraging Cognitive Latent Reasoning for Hierarchical Parallel Trajectory Planning in Autonomous Driving

2025-12-28 · Qihang Peng, Xuesong Chen, Chenye Yang, Shaoshuai Shi 외 arxiv

Autonomous driving requires generating safe and reliable trajectories from complex multimodal inputs. Traditional modular pipelines separate perception, prediction, and planning, while recent end-to-end (E2E) systems lea…

Scene UnderstandingTrajectory PlanningContinuous ControlAutonomous Driving

Multimodal Transformer for Parallel Concatenated Variational Autoencoders

2022-10-28 · Stephen D. Liang, Jerry M. Mendel

In this paper, we propose a multimodal transformer using parallel concatenated architecture. Instead of using patches, we use column stripes for images in R, G, B channels as the transformer input. The column stripes kee…

Decoder

Parallelizing Autoregressive Generation with Variational State Space Models

2024-07-11 · Gaspard Lambrechts, Yann Claes, Pierre Geurts, Damien Ernst

Attention-based models such as Transformers and recurrent models like state space models (SSMs) have emerged as successful methods for autoregressive sequence modeling. Although both enable parallel training, none enable…

DecoderMambaState Space ModelsText Generation

Reasoning as Energy Minimization over Structured Latent Trajectories

2026-03-30 · David K. Johansson arxiv

Single-shot neural decoders commit to answers without iterative refinement, while chain-of-thought methods introduce discrete intermediate steps but lack a scalar measure of reasoning progress. We propose Energy-Based Re…

DITTO: Dual and Integrated Latent Topologies for Implicit 3D Reconstruction

2024-03-08 · CVPR 2024 1 · Jaehyeok Shim, Kyungdon Joo

We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, suc…

3D ReconstructionDecoder