{"id":"2606.26120","title":"Dynamic-dLLM: Dynamic Cache-Budget and Adaptive Parallel Decoding for Training-Free Acceleration of Diffusion LLM","url":"https://codeofpaper.com/paper/2606.26120","arxiv_url":"https://arxiv.org/abs/2606.26120","published":"2026-05-27","code":"none","best":null,"most_starred_community":null,"implementations":[],"possible_matches":0}