Newest papers

Large Flow Language Models

Arnav Chavan, Chanhyuk Lee, Udbhav Bamba, Jaehoon Yoo, Seunghoon Hong, Aditi Raghunathan, Jinwoo Kim · 2026 · arXiv

DOI: 10.48550/arXiv.2610.28559 · open-access PDF

Korean

지속적인 흐름 언어 모델은 분리된 확산을 위해 사용할 수없는 제어 및 가속 도구로 병렬 생성에 대한 경로를 제공하지만, 수십억 매개 변수 규모에서 그들을 구축하는 효과적인 기술은 덜 확립되어 있습니다. 우리는 Lafa (Large Flow Language Model)를 제시합니다.이 디자인은 데이터 효율적인 방식으로 8B 매개 변수로 확장된 빠르고 높은 성능의 흐름 언어 모델입니다.Lafa는 사전 및 각 블록 내의 양방향, 비동기 흐름에 대한 원인 관심을 가진 블록 방향의 흐름 모델입니다.이 디자인은 사전 훈련 된 자율 반응 (AR) 모델 및 f를 적응함으로써 효율적인 훈련을 가능하게합니다.

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

Abstract

Continuous flow language models offer a path to parallel generation with tools for control and acceleration unavailable to discrete diffusion, yet effective techniques for building them at the billion-parameter scale remain less established. We present Lafa (Large flow language model), a fast, high-performing flow language model scaled to 8B parameters in a data-efficient manner. Lafa is a blockwise flow model with causal attention on the prefix and bidirectional, asynchronous flow within each block. This design enables efficient training by adapting pretrained autoregressive (AR) models and f

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

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28559, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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