一作ACL 2026Poster· Natural Language Processing
Towards Efficient and Effective Diffusion Language Model Inference via Semantic-Aware Adaptive Denoising
Fan Li · Yu Gu · Zhigang Wang · Fangling Leng · Zhenghao Liu · Ge Yu
摘要
Diffusion language models (DLMs) have emerged as a powerful non-autoregressive alternative to GPT-style sequential generation, but suffer from substantial computational overhead due to their iterative parallel denoising. Existing acceleration works cannot accurately detect semantically stabilized...