Newest papers

Parallel Language Models via Variational Decoding

Felix Draxler, Robin C. Geyer, Daniel Geyfman, Farrin Marouf Sofian, Justus Will, Philipp Hildebrandt, Giosue Migliorini, Prakhar Srivastava · 2026 · arXiv

DOI: 10.48550/arXiv.2610.26693 · open-access PDF

Japanese

Autoregressive 言語モデルは、前進パスごとに 1 つのトークンを発行します。これは、特にモデルが品質のためにスケーリングされているため、高い推測遅延を引き起こします。この論文では、共通言語モデル(PLMs)を導入します。これらのモデルは、後進パスごとに相互に一致したトークンを生成し、潜在的補助変数を通じて依存性をルーティングします。PLMsは、変数線を使用してトレーニングされます。

Machine translation (Meta M2M100); the English original follows.

Abstract

Autoregressive language models emit one token per forward pass. This causes high inference latency, in particular as models are scaled up for quality. In this paper, we introduce Parallel Language Models (PLMs), which generate mutually consistent tokens in one forward pass by routing dependencies through latent auxiliary variables. PLMs are trained using a variational bound that reduces to an autoregressive loss plus a parallel decoding loss. Empirically, PLMs are on a faster and better Pareto frontier than autoregressive and discrete diffusion baselines. Pretrained PLMs achieve near-autoregre

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange