Miltos Kofinas
@miltoskofinas.bsky.social
Postdoctoral researcher @vuamsterdam.bsky.social
AI for climate | Graph Neural Networks | Geometric Deep Learning | Neural Fields | Spatiotemporal Forecasting
mkofinas.github.io
AI for climate | Graph Neural Networks | Geometric Deep Learning | Neural Fields | Spatiotemporal Forecasting
mkofinas.github.io
Pinned
🧐How can we design neural networks that process other neural networks?
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.
Reposted by Miltos Kofinas
Here is tomorrow’s program. We’re meeting at 11 a.m. at the Garenmarktplein in Leiden. The program starts at 11.30. The teach outs are throughout the day in The Hague and Leiden: www.universiteitleiden.nl/en/news/2025...
10 maart: Universiteit Leiden start estafettestaking tegen bezuinigingen
Medewerkers van de Universiteit Leiden trappen maandag 10 maart de estafettestaking af van de Nederlandse universiteiten tegen de kabinetsbezuinigingen.
www.universiteitleiden.nl
March 9, 2025 at 12:09 PM
Here is tomorrow’s program. We’re meeting at 11 a.m. at the Garenmarktplein in Leiden. The program starts at 11.30. The teach outs are throughout the day in The Hague and Leiden: www.universiteitleiden.nl/en/news/2025...
🎉 Delighted to start my postdoc at @vuamsterdam.bsky.social, working with Dim Coumou
and Eliot Walt on AI for climate & foundation models for weather forecasting. Climate change is one of the most urgent challenges of our time, and I am excited to use my expertise in AI to tackle it. 🌎🌍🌏
and Eliot Walt on AI for climate & foundation models for weather forecasting. Climate change is one of the most urgent challenges of our time, and I am excited to use my expertise in AI to tackle it. 🌎🌍🌏
February 7, 2025 at 10:31 AM
🎉 Delighted to start my postdoc at @vuamsterdam.bsky.social, working with Dim Coumou
and Eliot Walt on AI for climate & foundation models for weather forecasting. Climate change is one of the most urgent challenges of our time, and I am excited to use my expertise in AI to tackle it. 🌎🌍🌏
and Eliot Walt on AI for climate & foundation models for weather forecasting. Climate change is one of the most urgent challenges of our time, and I am excited to use my expertise in AI to tackle it. 🌎🌍🌏
Exciting application of neural graphs for weight nowcasting! With new and improved neural graphs for Transformers!
x.com/BorisAKnyazev/…
x.com/BorisAKnyazev/…
February 7, 2025 at 10:20 AM
Exciting application of neural graphs for weight nowcasting! With new and improved neural graphs for Transformers!
x.com/BorisAKnyazev/…
x.com/BorisAKnyazev/…
🧐How can we design neural networks that process other neural networks?
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.
February 7, 2025 at 10:20 AM
🧐How can we design neural networks that process other neural networks?
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.
The answer is simple: represent them as graphs, a.k.a. neural graphs!
Join our oral presentation and our poster at #ICLR2024 for more details.
Oral session 4B @ Halle A7 and poster #77 session 4 @ Halle B.
🔍How can we design neural networks that take neural network parameters as input?
🧪Our #ICLR2024 oral on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" answers this question!
📜:💻:🧵 [1/9
github.com/mkofinas/neura… arxiv.org/abs/2403.12143
🧪Our #ICLR2024 oral on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" answers this question!
📜:💻:🧵 [1/9
github.com/mkofinas/neura… arxiv.org/abs/2403.12143
February 7, 2025 at 10:19 AM
🔍How can we design neural networks that take neural network parameters as input?
🧪Our #ICLR2024 oral on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" answers this question!
📜:💻:🧵 [1/9
github.com/mkofinas/neura… arxiv.org/abs/2403.12143
🧪Our #ICLR2024 oral on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" answers this question!
📜:💻:🧵 [1/9
github.com/mkofinas/neura… arxiv.org/abs/2403.12143
🎉 Super stoked that our work on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" was accepted as an oral in #ICLR2024!
Paper details and source code will follow soon.
Paper details and source code will follow soon.
February 7, 2025 at 10:19 AM
🎉 Super stoked that our work on "Graph Neural Networks for Learning Equivariant Representations of Neural Networks" was accepted as an oral in #ICLR2024!
Paper details and source code will follow soon.
Paper details and source code will follow soon.
Join our poster on "Data Augmentations in Deep Weight Spaces" @neur_reps workshop, #NeurIPS2023, Ballroom A+B at 4pm!
February 7, 2025 at 10:19 AM
Join our poster on "Data Augmentations in Deep Weight Spaces" @neur_reps workshop, #NeurIPS2023, Ballroom A+B at 4pm!
Today at #NeurIPS2023 I will be presenting our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields".
Join us at poster session 3 on Wednesday morning, poster #619.
Paper:Source code:1/8] 🧵
github.com/mkofinas/aether arxiv.org/abs/2310.20679
Join us at poster session 3 on Wednesday morning, poster #619.
Paper:Source code:1/8] 🧵
github.com/mkofinas/aether arxiv.org/abs/2310.20679
February 7, 2025 at 10:19 AM
Today at #NeurIPS2023 I will be presenting our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields".
Join us at poster session 3 on Wednesday morning, poster #619.
Paper:Source code:1/8] 🧵
github.com/mkofinas/aether arxiv.org/abs/2310.20679
Join us at poster session 3 on Wednesday morning, poster #619.
Paper:Source code:1/8] 🧵
github.com/mkofinas/aether arxiv.org/abs/2310.20679
Thrilled to be in New Orleans for #NeurIPS2023! 🎉
Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.
Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.
February 7, 2025 at 10:19 AM
Thrilled to be in New Orleans for #NeurIPS2023! 🎉
Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.
Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.
February 7, 2025 at 10:19 AM
A little late for the party, but I am truly excited that our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields" was accepted at @NeurIPSConf! 😊
Wonderful collaboration with @erikjbekkers, @nsn86, and @egavves.
Details & source code coming soon!
Wonderful collaboration with @erikjbekkers, @nsn86, and @egavves.
Details & source code coming soon!
February 7, 2025 at 10:19 AM
A little late for the party, but I am truly excited that our work on "Latent Field Discovery in Interacting Dynamical Systems with Neural Fields" was accepted at @NeurIPSConf! 😊
Wonderful collaboration with @erikjbekkers, @nsn86, and @egavves.
Details & source code coming soon!
Wonderful collaboration with @erikjbekkers, @nsn86, and @egavves.
Details & source code coming soon!
How can we effectively use neural networks to process the parameters of other neural nets?
We propose representing neural networks as computation graphs, enabling the use of standard graph neural networks to preserve permutation symmetries.
Join our poster @TAGinDS in #ICML2023!
We propose representing neural networks as computation graphs, enabling the use of standard graph neural networks to preserve permutation symmetries.
Join our poster @TAGinDS in #ICML2023!
February 7, 2025 at 10:19 AM
How can we effectively use neural networks to process the parameters of other neural nets?
We propose representing neural networks as computation graphs, enabling the use of standard graph neural networks to preserve permutation symmetries.
Join our poster @TAGinDS in #ICML2023!
We propose representing neural networks as computation graphs, enabling the use of standard graph neural networks to preserve permutation symmetries.
Join our poster @TAGinDS in #ICML2023!
Today at #ICML2023 I will be co-presenting "Graph Switching Dynamical Systems". Join us in poster session 2, poster 636.
Joint work with Yongtuo Liu, @saramagliacane and @egavves.
Arxiv:Github:
github.com/yongtuoliu/Gra… arxiv.org/abs/2306.00370
Joint work with Yongtuo Liu, @saramagliacane and @egavves.
Arxiv:Github:
github.com/yongtuoliu/Gra… arxiv.org/abs/2306.00370
Graph Switching Dynamical Systems
Dynamical systems with complex behaviours, e.g. immune system cells interacting with a pathogen, are commonly modelled by splitting the behaviour into different regimes, or modes, each with...
arxiv.org
February 7, 2025 at 10:18 AM
Today at #ICML2023 I will be co-presenting "Graph Switching Dynamical Systems". Join us in poster session 2, poster 636.
Joint work with Yongtuo Liu, @saramagliacane and @egavves.
Arxiv:Github:
github.com/yongtuoliu/Gra… arxiv.org/abs/2306.00370
Joint work with Yongtuo Liu, @saramagliacane and @egavves.
Arxiv:Github:
github.com/yongtuoliu/Gra… arxiv.org/abs/2306.00370
Excited to be in Hawaii for #ICML2023! Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.
February 7, 2025 at 10:18 AM
Excited to be in Hawaii for #ICML2023! Ping me if you want to grab a coffee and chat about graph networks, geometric deep learning, and neural fields.
Next up at #icvss2023, the inspirational @karpathy on ChatGPT from scratch!
February 7, 2025 at 10:18 AM
Next up at #icvss2023, the inspirational @karpathy on ChatGPT from scratch!
Kicking off #icvss2023 with generative models by @phillip_isola
February 7, 2025 at 10:18 AM
Kicking off #icvss2023 with generative models by @phillip_isola
A little late for the appraisal, but #GeMSS23 was a blast! I had many engaging discussions with fellow students! Many thanks to @jesfrellsen, @jmtomczak, and @pamattei for the amazing organization, as well as all the invited speakers for in-depth lectures!
February 7, 2025 at 10:18 AM
A little late for the appraisal, but #GeMSS23 was a blast! I had many engaging discussions with fellow students! Many thanks to @jesfrellsen, @jmtomczak, and @pamattei for the amazing organization, as well as all the invited speakers for in-depth lectures!
"Neural Fields across Fields" workshop @iclr_conf happening now! Visit our poster on "Neural Fields for Latent Force Field Discovery in Interacting Systems".
x.com/hyunjik11/stat…
x.com/hyunjik11/stat…
February 7, 2025 at 10:18 AM
"Neural Fields across Fields" workshop @iclr_conf happening now! Visit our poster on "Neural Fields for Latent Force Field Discovery in Interacting Systems".
x.com/hyunjik11/stat…
x.com/hyunjik11/stat…
Excited to be in Kigali @iclr_conf! Ping me if you are also here and you want to have a chat. 🙂 I work on graph networks, equivariance, interacting systems, and neural fields.
February 7, 2025 at 10:18 AM
Excited to be in Kigali @iclr_conf! Ping me if you are also here and you want to have a chat. 🙂 I work on graph networks, equivariance, interacting systems, and neural fields.
Yesterday we had an excellent and thought-provoking talk by @SergeBelongie on "representation learning for narratives in social media", that concluded the @ASCI_NL "Computer Vision by Learning" course. Looking forward to upcoming publications on the topic!
February 7, 2025 at 10:18 AM
Yesterday we had an excellent and thought-provoking talk by @SergeBelongie on "representation learning for narratives in social media", that concluded the @ASCI_NL "Computer Vision by Learning" course. Looking forward to upcoming publications on the topic!
Join us tomorrow for a discussion on local coordinate frames for interacting objects in geometric graphs. Thank you very much @HannesStaerk for the invitation!
x.com/HannesStaerk/s…
x.com/HannesStaerk/s…
February 7, 2025 at 10:18 AM
Join us tomorrow for a discussion on local coordinate frames for interacting objects in geometric graphs. Thank you very much @HannesStaerk for the invitation!
x.com/HannesStaerk/s…
x.com/HannesStaerk/s…
We have just released the source code for 𝗟𝗼𝗖𝗦, "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems":
x.com/MiltosKofinas/… github.com/mkofinas/locs
x.com/MiltosKofinas/… github.com/mkofinas/locs
Excited to share that our paper "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems" was accepted to #NeurIPS2021. Joint work with @nsn86 and @egavves.
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
Modelling interactions is critical in learning complex dynamical systems, namely systems of interacting objects with highly non-linear and time-dependent behaviour. A large class of such systems...
arxiv.org
February 7, 2025 at 10:18 AM
We have just released the source code for 𝗟𝗼𝗖𝗦, "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems":
x.com/MiltosKofinas/… github.com/mkofinas/locs
x.com/MiltosKofinas/… github.com/mkofinas/locs
Local coordinate frames are a simple yet effective way to introduce roto-translation equivariance and object-centric perspectives in interacting systems.
Want to learn more? Visit us today at #NeurIPS2021 Poster Session 6, at 5:30 pm CET.
Poster:
x.com/MiltosKofinas/… neurips.cc/virtual/2021/p…
Want to learn more? Visit us today at #NeurIPS2021 Poster Session 6, at 5:30 pm CET.
Poster:
x.com/MiltosKofinas/… neurips.cc/virtual/2021/p…
Excited to share that our paper "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems" was accepted to #NeurIPS2021. Joint work with @nsn86 and @egavves.
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
Modelling interactions is critical in learning complex dynamical systems, namely systems of interacting objects with highly non-linear and time-dependent behaviour. A large class of such systems...
arxiv.org
February 7, 2025 at 10:18 AM
Local coordinate frames are a simple yet effective way to introduce roto-translation equivariance and object-centric perspectives in interacting systems.
Want to learn more? Visit us today at #NeurIPS2021 Poster Session 6, at 5:30 pm CET.
Poster:
x.com/MiltosKofinas/… neurips.cc/virtual/2021/p…
Want to learn more? Visit us today at #NeurIPS2021 Poster Session 6, at 5:30 pm CET.
Poster:
x.com/MiltosKofinas/… neurips.cc/virtual/2021/p…
Excited to share that our paper "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems" was accepted to #NeurIPS2021. Joint work with @nsn86 and @egavves.
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
Modelling interactions is critical in learning complex dynamical systems, namely systems of interacting objects with highly non-linear and time-dependent behaviour. A large class of such systems...
arxiv.org
February 7, 2025 at 10:17 AM
Excited to share that our paper "Roto-translated Local Coordinate Frames For Interacting Dynamical Systems" was accepted to #NeurIPS2021. Joint work with @nsn86 and @egavves.
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961
Paper:Source code:1/6
github.com/mkofinas/locs arxiv.org/abs/2110.14961