from Hacker News

Block Diffusion: Interpolating Autoregressive and Diffusion Language Models

by t55 on 5/8/25, 6:18 PM with 16 comments

  • by macawfish on 5/9/25, 12:36 AM

    Wow.

    I can't wait to see ideas from the diffusion image generation world (like controlnet) work their way into language models.

  • by notrealyme123 on 5/8/25, 8:50 PM

    This was posted here already a few weeks ago.
  • by holoduke on 5/8/25, 9:11 PM

    Whenever I try to read and understand this paper, I feel extremely dumb. I have my degree in CS, but this is just too complex for me to understand.
  • by gitroom on 5/9/25, 4:02 AM

    Yeah I always end up lost in papers like this too, even with my CS degree, the research keeps leveling up nonstop.