@martinca.bsky.social
MS AI @ VU Amsterdam - Interested in Geometrical Deep Learning | Topological Deep Learning | Graphs
It is very refreshing seeing the start of a summer school be about Ethics in AI calling out the hype on GenAI as the frontier of human reasoning. Listening to this I am reminded of Feyerabend…
“The only absolute truth is that there are no absolute truths”
#EDS2025
“The only absolute truth is that there are no absolute truths”
#EDS2025
August 25, 2025 at 12:02 PM
It is very refreshing seeing the start of a summer school be about Ethics in AI calling out the hype on GenAI as the frontier of human reasoning. Listening to this I am reminded of Feyerabend…
“The only absolute truth is that there are no absolute truths”
#EDS2025
“The only absolute truth is that there are no absolute truths”
#EDS2025
The model relies on positional and structural encodings (PSE) of the combinatorial domain. By decomposing a combinatorial representation into neighborhoods which take the form of a Hasse graph, the PSE of each can be used to discard the topology and learn from the PSE!
(4/6)
(4/6)
May 26, 2025 at 11:17 AM
The model relies on positional and structural encodings (PSE) of the combinatorial domain. By decomposing a combinatorial representation into neighborhoods which take the form of a Hasse graph, the PSE of each can be used to discard the topology and learn from the PSE!
(4/6)
(4/6)
🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better?
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
May 26, 2025 at 11:17 AM
🚨Higher-order combinatorial models in TDL are notoriously slow and resource-hungry. Can we do better?
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
Introducing:
🚀 𝐇𝐎𝐏𝐒𝐄: A Scalable Higher-Order Positional and Structural Encoder for Combinatorial Representations 🚀
📝 arXiv: arxiv.org/abs/2505.15405
🧵 (1/6)
It came! Excited that I will be attending @logml.bsky.social in London the second week of July, I am happy to connect with fellow colleagues interested in geometry, topology and graphs in ML :) 🛟
May 1, 2025 at 6:58 PM
It came! Excited that I will be attending @logml.bsky.social in London the second week of July, I am happy to connect with fellow colleagues interested in geometry, topology and graphs in ML :) 🛟