{"ID":2835292,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.00670","arxiv_id":"2512.00670","title":"EDIT: Early Diffusion Inference Termination for dLLMs Based on Dynamics of Training Gradients","abstract":"Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete. We propose EDIT (Early Diffusion Inference Termination), an inference-time criterion that adaptively stops denoising once sufficient reasoning stability relative to training-time reasoning is detected. EDIT monitors the alignment between token activations and a reasoning map derived from AdamW-aggregated LoRA updates captured during supervised fine-tuning (SFT). During training, optimization dynamics generate rich metadata about parameter importance that in prior methods is typically discarded upon model release. We preserve this information as a compact representation of learned reasoning pathways. During inference, alignment scores are converted to a distribution over the tokens already unmasked at the current denoising step, and convergence is detected when KL divergence between consecutive steps falls below a threshold on the matched unmasked (visible) tokens. Across reasoning benchmarks, EDIT reduces diffusion steps by 11.8% to 68.3% while preserving or improving accuracy in most settings, with approximately 0.02% storage overhead (about 1.5-2 MB for all QKV modules across 32 blocks in an 8 GB model). By utilizing training-gradient dynamics, our work opens a new research direction for reducing dLLM inference time and cost.","short_abstract":"Diffusion-based large language models (dLLMs) refine token generations through iterative denoising, but answers often stabilize before all steps complete. We propose EDIT (Early Diffusion Inference Termination), an inference-time criterion that adaptively stops denoising once sufficient reasoning stability relative to...","url_abs":"https://arxiv.org/abs/2512.00670","url_pdf":"https://arxiv.org/pdf/2512.00670v1","authors":"[\"He-Yen Hsieh\",\"Hong Wang\",\"H. T. Kung\"]","published":"2025-11-29T23:47:47Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Large Language Model\",\"Language Model\",\"LoRA\"]","has_code":false}