AI RESEARCH
WaveFilter: Enhancing the Long-Context Capability of Diffusion LLMs via Wavelet-Guided KV Cache Filtering
arXiv CS.AI
•
ArXi:2606.00724v1 Announce Type: cross Diffusion Large Language Models (DLMs) have nstrated significant advantages across various tasks. However, constrained by their multi-step iterative inference mechanism, their computational overhead and inference latency in long-context tasks have become core bottlenecks restricting their large-scale deployment.