{"slug": "masked-language-flow-models", "title": "Masked Language Flow Models", "summary": "Researchers introduced Masked Language Flow Models (MLFMs), combining masked diffusion and flow-based methods for efficient language generation. MLFMs enable conditional generation via continuous flows and support multi-step reasoning through a novel alternating sampler. Evaluations on GSM8K and MT-Bench show flow-based language models can scale to reasoning and instruction-following tasks.", "body_md": "arXiv:2606.27617v1 Announce Type: new\nAbstract: Masked Diffusion Models (MDMs) promise fast, parallel language generation, but their reverse transition factorises across token positions -- an approximation that breaks down in the few-step sampling regime where parallel generation ought to provide the greatest efficiency gains. Flow Language Models (FLMs) sidestep this limitation by learning a continuous flow that transports noise toward clean sequences represented in Euclidean space, inducing a flow map that can be distilled for single-step generation. However, this makes complex tasks requiring multi-step reasoning problematic for FLMs, as FLMs are forced to decode every token during generation. To address this, we introduce Masked Language Flow Models (MLFMs), which incorporate masking into FLMs using a continuous stochastic interpolant to bridge partially masked and clean sequences. This design enables conditional generation via continuous flows and allows pretrained MDMs to be converted into MLFMs through a simple, lightweight adaptation. Leveraging this flexibility, we propose a novel sampler that alternates continuous denoising with the discrete unmasking of confident tokens to better support multi-step reasoning. We evaluate our approach on GSM8K and MT-Bench and find, for the first time, that flow-based language models can be scaled to solve downstream reasoning and instruction-following tasks.", "url": "https://wpnews.pro/news/masked-language-flow-models", "canonical_source": "https://arxiv.org/abs/2606.27617", "published_at": "2026-06-29 04:00:00+00:00", "updated_at": "2026-06-29 04:07:37.337232+00:00", "lang": "en", "topics": ["large-language-models", "generative-ai", "natural-language-processing", "ai-research", "machine-learning"], "entities": ["Masked Language Flow Models", "Masked Diffusion Models", "Flow Language Models", "GSM8K", "MT-Bench"], "alternates": {"html": "https://wpnews.pro/news/masked-language-flow-models", "markdown": "https://wpnews.pro/news/masked-language-flow-models.md", "text": "https://wpnews.pro/news/masked-language-flow-models.txt", "jsonld": "https://wpnews.pro/news/masked-language-flow-models.jsonld"}}