04:00
2026-08-11
arxiv.org
machine-learning
Archer: Adaptive Reuse of Cached Hidden States for Efficient Rollback in Diffusion Language Models
Researchers introduced Archer, a training-free KV caching method for diffusion language models that achieves a 2.57x mean speedup and 33.63% mean performance on the main suite, improving Pass@1 by up …