AI RESEARCH
FlowLM: Few-Step Language Modeling via Diffusion-to-Flow Adaptation
arXiv CS.CL
•
ArXi:2605.20199v1 Announce Type: new We present FlowLM, a flow matching language model transformed from pre-trained diffusion language models via efficient fine-tuning. By re-aligning the curved sampling trajectories of diffusion models into straight-line flows, FlowLM enables high quality few-step generation that rivals or even outperforms the quality of 2,000-step diffusion sampling with very few