Polestar: Drift-Aware Cache Calibration and Token Commitment for Efficient Inference of Diffusion LLMs

Jul 17, 2026

Polestar is a training-free inference framework for diffusion large language models (dLLMs) that leverages token representation drift to address inefficiencies in KV-cache reuse and challenges in decoding parallelism. It introduces Polestar-Cache for selective KV-cache refreshes and Polestar-Commit for identifying commit-ready tokens. Experiments show Polestar achieves up to 10.73% accuracy improvement and up to 3.7x higher throughput compared to existing baselines on mathematics and coding benchmarks.

Why it matters: This work demonstrates a significant advance in the efficient inference of diffusion LLMs, potentially accelerating their adoption as an alternative to autoregressive models.

Full story at: arXiv Computation and Language ↗