Janis Postels

[Janis Postels @JanisPostels]

Will be presenting our work "On the Practicality of Deterministic Epistemic Uncertainty" next week at #ICML2022 in Baltimore.

If you are interested checkout our paper or visit us at our poster on
Tue Jul 19 between 06:30 PM & 08:30 PM @ Hall E 506

https://t.co/2kCrqhEg7R

[Janis Postels @JanisPostels]

Looking forward to this :)

[Bertrand Charpentier @Bertrand_Charp]

Jakob Heiss will present his ICML paper "NOMU - Neural Optimization-based Model Uncertainty" at the Uncertainty in AI reading group today at 5:30pm (Berlin time).

https://t.co/WhU4wqjAmf

Co-author: @JWeissteiner, Hanna Wutte, @SvenSeuken, Josef Teichmann

[Janis Postels @JanisPostels]

@mentzer_f Congrats 🎉

[Janis Postels @JanisPostels]

Will be presenting our work "ManiFlow: Implicitly Representing Manifolds with Normalizing Flows" at #3DV tomorrow!

We show how to sample from manifolds (e.g. Point Clouds) with normalizing flows!

@MDanelljan Luv Van Gool @fedassa

Paper: https://t.co/THu0XCkk8n

[Janis Postels @JanisPostels]

@lilianweng Great summary! Would have saved me a lot of time if I'd seen it a little earlier :-D

[Janis Postels @JanisPostels]

Further, we invite you to share your recent/ongoing work in this area. There will be a total prize pool of up to 1500$ distributed among the best submissions.

https://t.co/WMSGLk8qfS)

[Janis Postels @JanisPostels]

Very happy to announce our workshop on Probabilistic Robotics at #IROS 2022 in Kyoto. 

https://t.co/fcDrAamG4k

Jointly organized with

@FengJianxiang @JongseokLee11 @matthiashumt @YizheWu5 Rudolph Triebel

[Janis Postels @JanisPostels]

This WS brings together experts from both fields - probabilistic methods in robotics and deep learning - to provide a forum for this urgent topic.

@wolfram_burgard @contactrika @nikoSuenderhauf  Fabio Ramos  Teresa Vidal  @yaringal  Ali Agha  @balajiln  @padsmagt  @IngmarPosner

[Markus Nagel @mnagel87]

If your are at #ICML2022, join us Thursday at 11:00 in the Ballroom 1&2 for our oral presentation on "Overcoming Oscillations in Quantization-Aware Training" and later at poster #227.
Paper: https://t.co/cCE07iN5Mq
@mfournarakis, @yell1337, @TiRune.

[Augustine Mavor-Parker @MavorParker]

Would you rather play games or watch random images? In our #ICML2022 work, we give RL agents this choice and turns out many curiosity algos would prefer to watch random images. We propose an acetylcholine-inspired solution to help curiosity to avoid these "noisy TVs"

[Auke Wiggers @aukejw]

The MobileCodec paper is now online: https://t.co/9E27v5Vrtd

Check it out if you want to know how we were able to deploy a neural video codec to a mobile phone and decode 720p video in real time 📲

[Ferjad Naeem @ferjadnaeem]

I am excited to share that our work "3D Compositional Zero-shot Learning with DeCompositional Consensus" has been accepted at #ECCV2022. Joint work with @evinpinar @xyongqin, Luc Van Gool and @fedassa between ETH Zurich, TUM, and Google. https://t.co/0mULaZUs8l [1/7]

[Janis Postels @JanisPostels]

@abursuc Congrats! Let me know when the preprint is available. Looking forward to that work and seeing you at ECCV!

[Janis Postels @JanisPostels]

Will be presenting our work "On the Practicality of Deterministic Epistemic Uncertainty" next week at #ICML2022 in Baltimore.

If you are interested checkout our paper or visit us at our poster on
Tue Jul 19 between 06:30 PM & 08:30 PM @ Hall E 506

https://t.co/2kCrqhEg7R

[Janis Postels @JanisPostels]

We shed light onto a recent trend in uncertainty quantification which treats the weights of DNNs deterministically.

Turns despite good OOD detection these methods do not necessarily yield well calibrated uncertainty.

[Janis Postels @JanisPostels]

Great work guys!

[Mattia Segu @MattiaSegu]

@CVPR time has finally come!

Check out our paper "SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation" and drop by our poster session on Friday 24 (afternoon) at 257B to learn more!

Project Page: https://t.co/CUuvcNY0TN
Paper: https://t.co/3b2IZMNZNP

[Andrei Bursuc @abursuc]

Cool new AD dataset in town 👉 SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation by @JanisPostels @MattiaSegu @DrFisherYu @fedassa et al. https://t.co/CYfMv8tRlA 1/

[Janis Postels @JanisPostels]

Single NFs struggle to model geometries with different geometric properties than the base distribution (e.g. transforming a Gaussian into a ring-shaped distribution)

We show that mixtures of NFs are strong inductive bias to overcome this problem in a parameter-efficient way.

[Janis Postels @JanisPostels]

Glad to share that we will present our work "Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction" tomorrow at 3DV.

Paper: https://t.co/Qwt85h435W

Code: https://t.co/Z0i0bf10jl

Poster at 11:20am GMT (03.12.)/00:20am GMT (04.12.)

>>

[Janis Postels @JanisPostels]

@prunetruong Congrats :-)

[Federico Tombari @fedassa]

Our work on Variational Transformer Networks for layout generation got featured on the Google AI blog. The work will be presented at CVPR21 on June 24th and a pre-release is available on arXiv.

Blog post:
Official Tweet: https:/…https://t.co/FMRjuuLI2u https://t.co/SlGnqZDCZB