Alex Foo

PhD Candidate @NUSingapore • Interested in Object-Centric and Causal Representation Learning for Computer Vision

[Alex Foo @alexfoo_dw]

Thrilled to share my first explainer video! 🥳

Here's my attempt at giving an animated, from-the-ground-up overview on graph neural networks.

Would love to hear what you found helpful and what can be better!!

https://t.co/jWgkYXnmRI

[Simone Scardapane @s_scardapane]

*Relative representations enable zero-shot latent space communication*

If you liked git re-basin: embeddings from distinct nets may be equal up to isometry, and switching representation can enable zero-shot combination of separate pre-trained components.

https://t.co/6UL0U72DBc

[Pietro Barbiero @pietro_barbiero]

Beyond the accuracy-explainability tradeoff with "Concept Embedding Models" from #NeurIPS (https://t.co/yZKYvJX2Fa): moving towards trustworthy #AI!

Light reading mode: https://t.co/UwzTsIYySs

[CLeaR-Conference on Causal Learning and Reasoning @Conf_CLeaR]

**Reminder** 1 month to submit your #causal papers to #CLeaR2023 and then join us in April in beautiful Tübingen 🇩🇪🏰🍻 #causalInference #causalDiscovery #causalLearning #causalML #causalRepresentationLearning

[CLeaR-Conference on Causal Learning and Reasoning @Conf_CLeaR]

CLeaR 2023 submission is open💥: https://t.co/ZYWDmTP2oM

We welcome submissions about new #theory, #methodology or #applications relevant to any aspect of #causal learning and reasoning in #AI, #ML and #stats

Deadline is Oct 28 11:59pm AoE, details here:
https://t.co/AdNPafgnwo

[Thomas Kipf @tkipf]

Our latest work at @GoogleAI on emergent object-centric learning will be presented at @NeurIPSConf this year:

1) OSRT: Object Scene Representation Transformer

https://t.co/daN3LPFJHJ

[Petar Veličković @PetarV_93]

📢 New course! Cats4AI🐱🤖

Learn category theory foundations from the lens of ML, grounded in concrete papers. Open to all!

Sign up: https://t.co/WnbVfm3ju5

@andrewdudzik @bgavran3 @_joaogui1 @pimdehaan
+ fantastic speakers @math3ma @CollapsingPanda @david_i_spivak @TacoCohen

[Bastian Grossenbacher-Rieck @Pseudomanifold]

Hey y'all 👋! Please consider submitting your work to @LogConference. Abstracts are due on 9/9 AoE!

🔥 2 tracks: extended abstracts (4p) & full papers (9p)
🔥 focus on high-quality reviews
🔥 PMLR proceedings for accepted papers

Spread the word! 🙏

CfP: https://t.co/M9PBejhhTD

[CLeaR-Conference on Causal Learning and Reasoning @Conf_CLeaR]

The Causal Learning and Reasoning Conference (CLeaR) 2022 proceedings are out: https://t.co/tNoK0NELlr 🎉

Thanks to our publication chairs @ZhijingJin @alexdamour and program chairs @bschoelkopf @CarolineUhler @kunkzhang !

Coming soon: CLeaR 2023 CFP (deadline mid-Oct)

[Causal Representation Learning Workshop @ UAI'22 @crl_uai]

For those of you who could not attend, the slides and recording (unfortunately, afternoon only) of our UAI 2022 Causal Representation Learning Workshop are now available on the workshop website:
https://t.co/gnEL2PcloZ
https://t.co/VZfdK6nCY5

[Damien Teney @DamienTeney]

Some studies suggest in-/out-of-distribution performance are usually correlated. But sometimes it's the *opposite* when you look close enough!
➡️ There may be a necessary tradeoff.
➡️ ID Improvements by ERM or by model selection may be counterproductive to OOD generalization.

[Thomas Kipf @tkipf]

Excited to give a talk at the ELLIS Video Understanding Symposium this week! I will talk about our latest works on object-centric perception:

🎥 https://t.co/aG6sMzfg5u
📷 https://t.co/YLj92Mm2a1

[Matej Zečević @matej_zecevic]

This week in the Causality Discussion Group we have @JKugelgen discussing his recent NeurIPS 2021 paper on "Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style" (https://t.co/9tkGpxnmB5)

To join the session click on https://t.co/2iYr5bByRt 🌿

[Alex Foo @alexfoo_dw]

@sindy_loewe @wellingmax @AmlabUva @UvA_Amsterdam Congrats!! Well deserved

[CLeaR-Conference on Causal Learning and Reasoning @Conf_CLeaR]

The CLeaR society is delighted to announce that we are organizing the 2023 edition of CLeaR in Tubingen, Germany. The submission deadline will be around mid-October. Details will be released shortly. Please stay tuned!

[Alex Foo @alexfoo_dw]

@sairgotz Happy it helped! :)

[Jon Barron @jon_barron]

I am really impressed with these results. Giving Dalle/Imagen/StableDiffusion/WhateverComesNext the ability to reason about specific instances of objects is going to be hugely useful. https://t.co/S3UkghMm9O

[🔥囧Robert Osazuwa Ness囧🔥 @osazuwa]

A code first Causal AI book on https://t.co/DW6BxS8x9w Newsletter https://t.co/ZPXg78b7Dw

[Daniel Bear @recursus]

Excited to share our ECCV oral! https://t.co/ILBRfhVIDG

"Unsupervised Segmentation in Real-World Images via Spelke Object Inference"

A case of psych + neuroscience helping us build much better AI!

@honglin_c Rahul Venkatesh @_yonifriedman @jiajunwu_cs Josh Tenenbaum @dyamins

[Francesco Locatello @FrancescoLocat8]

We are hiring an industrial PhD student co-supervised by myself and @wielandbr at @aws_cloud and @mpi_is to work on identifiable object-centric representations. We would love to see applications from communities underrepresented in AI!

Apply here: https://t.co/nj3nKx3UpT