• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    Slides released for ECCV 2026 tutorial on diffusion model post-training

    The tutorial team's post lists direct reward gradient backpropagation, DPO, GRPO and forward-process RL as topics.

    Kosta DerpanisKD
    Liang ZhengLZ
    2 Sources, 3h ago, first seen 3h ago

    TLDR

    The team behind an ECCV 2026 tutorial says it has released slides on diffusion model post-training. Its post lists direct reward gradient backpropagation, DPO, GRPO and forward-process RL, and links to the tutorial schedule.

    Combined views

    2.9K

    2 Sources, first seen 3h ago

    Combined views

    2.9K

    2 Sources, first seen 3h ago

    80 likes
    80 likes
    1 comments
    54 saves
    29 reposts
    Featured Source
    1 comments
    54 saves
    29 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet

    2 Sources

    Liang Zheng@LiangZheng_06We've released the slides for our ECCV'26 tutorial on diffusion model post-training. - Direct reward gradient backpropagation; - DPO; - GRPO; - Forward-process RL. https://diffusion-alignment.github.io/#schedule Hope it will be useful for the community. @scxue1999 @zinho_leung @jie_liu13h
    Kosta Derpanis@CSProfKGDRT @LiangZheng_06: We've released the slides for our ECCV'26 tutorial on diffusion model post-training. - Direct reward gradient backprop…25m

    2 Sources

    Liang Zheng@LiangZheng_06We've released the slides for our ECCV'26 tutorial on diffusion model post-training. - Direct reward gradient backpropagation; - DPO; - GRPO; - Forward-process RL. https://diffusion-alignment.github.io/#schedule Hope it will be useful for the community. @scxue1999 @zinho_leung @jie_liu13h
    Kosta Derpanis@CSProfKGDRT @LiangZheng_06: We've released the slides for our ECCV'26 tutorial on diffusion model post-training. - Direct reward gradient backprop…25m