Large Flow Language Models
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 fast inference via prefix caching and blockwise parallel decoding. We train Lafa at 0.5B, 7B, and ...
| Authors | Arnav Chavan, Chanhyuk Lee, Udbhav Bamba et al. |
|---|---|
| Primary category | cs.CL |
| Published | 20 October 2026 |
| Last updated at source | 20 October 2026 |
Popularity, last 20 days
0 now. Counts as reported by the source, snapshotted daily by Silytics.
Connected in the knowledge graph
- lafa-hf/lafa-8BModel · cited by
- lafa-hf/lafa-0.5BModel · cited by
- lafa-hf/lafa-7BModel · cited by
Models and datasets referencing this paper
- lafa-hf/lafa-7BModel
- lafa-hf/lafa-0.5BModel
- lafa-hf/lafa-8BModel
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 9 November 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.