t3d-trajectory-distillation

【效率与协作】Accelerate diffusion language models from many to few generation steps using trajectory self-distillation. Collect clean-noisy state pairs along teacher trajectories, apply reverse-KL mode-seeking distillation, and weight losses by decoding order to prioritize early predictions where cascading errors compound.

独立 GitHub 快照 · 自动分类 · 以原作者文档为准