Chen Jian
Jian Chen is a Ph.D. student at UC San Diego in the Halıcıoğlu Data Science Institute, where he works on efficient machine learning with Prof. Zhijian Liu. He is a co-author of DFlash, a speculative decoding framework that uses a block diffusion model for parallel drafting to accelerate LLM inference, and MagicDec, a long-context speculative decoding method published at ICLR 2025. He previously completed a master's degree at Carnegie Mellon University and a research internship at Microsoft.
“I discussed with Chen Jian, the DFlash author; he raised a point important to the whole model — even with DFlash's advanced draft model strategy, its relationship to pretraining is still very significant.”
Source→“DFlash mentioned as advanced draft model strategy combining diffusion language model properties with autoregressive models”
Source→AI-extracted from podcast / newsletter / paper summaries. May contain errors.