#parallel-decoding

The latest AI and developer news about #parallel-decoding, with the original source and a short summary.

NVIDIA VFlash Reduces Robot Trajectory Prediction Latency by 5.1x

NVIDIA VFlash reduces latency by up to 5.1x for robot and autonomous driving trajectory prediction.

·2026.11.11 08:00

Beyond Next-Token Prediction: Performance Characteristics of Diffusion and Autoregressive Language Models

Diffusion language models enable parallel generation but showed limitations in long contexts and batch processing.

·1·2026.08.07 09:00

Parallel Decoding for Video Generation (10 min read)

Parallel Decoding Distillation predicts multiple denoising steps at once to improve the speed and diversity of video generation.

·2026.07.30 09:00

PickHPD-Parsing Achieves SoTA in Document Parsing

PaddlePaddle has released HPD-Parsing, a 1B document parsing model based on hierarchical parallel decoding, achieving the top score of 94.91% on OmniDocBench v1.6.

·1·2026.07.23 16:00

MBD-LM: Optimizing Parallel Generation for Diffusion-Based Language Models

The paper proposes MBD-LM, a Multi-Block approach designed to improve the parallel decoding performance of Block Diffusion Language Models (BD-LMs).

·2026.07.04 22:00

NVIDIA Releases Diffusion LM

NVIDIA has released a Diffusion language model family that delivers inference speeds up to 6x faster than existing AR models.

·2·2026.05.23 09:00