Thibaut Issenhuth retweeted
Today at #icml2024 - Workshop on
Structured Probabilistic Inference & Generative Modeling
📝Improving Consistency Models with Generator-Induced Coupling
👤@TIssenhuth, @LDosSantos_, @jy_franceschi, @rakotal1
🔗 arxiv.org/abs/2406.09570
🧡 @icmlconf
Thibaut Issenhuth retweeted
We are presenting our paper at #NeurIPS2023 on links between Grans and score-based diffusion models. Stop by at poster 521!
Thibaut Issenhuth retweeted
Looking forward to present at #NeurIPS2023, NOLA & Paris, a unification framework for diffusion models and GANs.
It opens up the possibility to train generators with diffusion and GANs without generators!
📜 openreview.net/forum?id=HMhE…
🖥️ github.com/White-Link/gpm
Thibaut Issenhuth retweeted
So happy to finally be able to talk about this paper "Unveiling the Latent Space Geometry of Push-Forward Generative Models" with @TIssenhuth, @ugotanielian and @JeremieMary
To me, it's an important paper, because we show that analysis and synthesis are linked.
🧵⬇️ (ICML'23)
Thibaut Issenhuth retweeted
EdiBERT: a generative model for image editing
Thibaut Issenhuth, Ugo Tanielian, Jeremie Mary, David Picard
openreview.net/forum?id=GRBb…
#gans #generative #encoders
"Do Not Mask What You Do Not Need to Mask: a Parser-Free Virtual Try-On" accepted at #ECCV2020: it runs 10x faster than SOTA and better preserves body details and accessories!
Paper: arxiv.org/abs/2007.02721
W. @CriteoAILab, @CCalauzenes,@JeremieMary
#ECCV








