Control Meets Learning Virtual Seminars (@ControlMeetsML) header
Control Meets Learning Virtual Seminars (@ControlMeetsML) profile picture

Control Meets Learning Virtual Seminars

@ControlMeetsML

Virtual seminar series on the intersection of control theory and machine learning

 Online
sites.google.com/view/control-meets-learning
Joined August 2020
  • Tweets54
  • Following0
  • Followers984
Control Meets Learning Virtual Seminars retweeted
Navid Azizan (@NavidAzizan) profile picture
Navid Azizan
@NavidAzizanOct 23
Paper: arxiv.org/abs/2511.08425 Code: github.com/azizanlab/HardFlo…
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via...

HardFlow: Hard-Constrained Sampling for Flow-Matching Models via...

Diffusion and flow-matching have emerged as powerful methodologies for generative modeling, with remarkable success in capturing complex data distributions and enabling flexible guidance at...

arxiv.org
MIT LIDS (@MITLIDS) profile pictureMIT LIDS@MITLIDSSep 16
When #AI operates in the physical world, “pretty close” may not cut it. LIDS researchers developed HardFlow, a method that helps pretrained generative AI satisfy hard constraints while improving solution quality — without retraining. bit.ly/4xydxBN
Image from MIT LIDS (@MITLIDS)
1
3
7
569
Load more