Stas Syrota
@mustas.bsky.social
Ph.D. @ DTU Compute (Cognitive Systems)
Personal website: https://syrota.me/
Github: https://github.com/mustass
Personal website: https://syrota.me/
Github: https://github.com/mustass
6/
👀 Learn more:
📝 Blog: syrota.me/posts/2025/0...
📄 Paper: syrota.me/files/identi...
🙏 With Eugene Zainchkovskyy, Quanhan Xi, Benjamin Bloem-Reddy, and Søren Hauberg.
👀 Learn more:
📝 Blog: syrota.me/posts/2025/0...
📄 Paper: syrota.me/files/identi...
🙏 With Eugene Zainchkovskyy, Quanhan Xi, Benjamin Bloem-Reddy, and Søren Hauberg.
Identifiable latent metric space: geometry as a solution to the identifiability problem
syrota.me
July 14, 2025 at 5:47 AM
6/
👀 Learn more:
📝 Blog: syrota.me/posts/2025/0...
📄 Paper: syrota.me/files/identi...
🙏 With Eugene Zainchkovskyy, Quanhan Xi, Benjamin Bloem-Reddy, and Søren Hauberg.
👀 Learn more:
📝 Blog: syrota.me/posts/2025/0...
📄 Paper: syrota.me/files/identi...
🙏 With Eugene Zainchkovskyy, Quanhan Xi, Benjamin Bloem-Reddy, and Søren Hauberg.
5/
📍 Presenting at ICML:
🗓️ Tuesday, 11:00 AM–1:30 PM
📌 West Exhibition Hall B2–B3
🎨 Poster: syrota.me/files/imsdlv...
📍 Presenting at ICML:
🗓️ Tuesday, 11:00 AM–1:30 PM
📌 West Exhibition Hall B2–B3
🎨 Poster: syrota.me/files/imsdlv...
syrota.me
July 14, 2025 at 5:46 AM
5/
📍 Presenting at ICML:
🗓️ Tuesday, 11:00 AM–1:30 PM
📌 West Exhibition Hall B2–B3
🎨 Poster: syrota.me/files/imsdlv...
📍 Presenting at ICML:
🗓️ Tuesday, 11:00 AM–1:30 PM
📌 West Exhibition Hall B2–B3
🎨 Poster: syrota.me/files/imsdlv...
4/
I’m especially curious about the implications for disentanglement and causality. Would love to chat with anyone working on these topics! 🔍
I’m especially curious about the implications for disentanglement and causality. Would love to chat with anyone working on these topics! 🔍
July 14, 2025 at 5:46 AM
4/
I’m especially curious about the implications for disentanglement and causality. Would love to chat with anyone working on these topics! 🔍
I’m especially curious about the implications for disentanglement and causality. Would love to chat with anyone working on these topics! 🔍
3/
Why does this matter?
Because it allows trustworthy computations of relations between latent variables — which is essential in scientific applications where latent variables are of interest.
It also strengthens reliability and explainability in generative models in general.
Why does this matter?
Because it allows trustworthy computations of relations between latent variables — which is essential in scientific applications where latent variables are of interest.
It also strengthens reliability and explainability in generative models in general.
July 14, 2025 at 5:46 AM
3/
Why does this matter?
Because it allows trustworthy computations of relations between latent variables — which is essential in scientific applications where latent variables are of interest.
It also strengthens reliability and explainability in generative models in general.
Why does this matter?
Because it allows trustworthy computations of relations between latent variables — which is essential in scientific applications where latent variables are of interest.
It also strengthens reliability and explainability in generative models in general.
2/
The core idea:
We prove that the pullback metric is identifiable.
This means geodesic distances, volumes, and optimal transport in latent space are now meaningful & model-invariant. ✅
The core idea:
We prove that the pullback metric is identifiable.
This means geodesic distances, volumes, and optimal transport in latent space are now meaningful & model-invariant. ✅
July 14, 2025 at 5:46 AM
2/
The core idea:
We prove that the pullback metric is identifiable.
This means geodesic distances, volumes, and optimal transport in latent space are now meaningful & model-invariant. ✅
The core idea:
We prove that the pullback metric is identifiable.
This means geodesic distances, volumes, and optimal transport in latent space are now meaningful & model-invariant. ✅