Louisa Cornelis (@louisacornelis) 's Twitter Profile
Louisa Cornelis

@louisacornelis

physics phd student at ucsb @geometric_intel, prev @onepeloton, cs and physics and art @scrippscollege @harveymudd

ID: 1775244744580632578

calendar_today02-04-2024 19:32:29

42 Tweet

95 Followers

50 Following

Fatih Dinc (@fatihdin4en) 's Twitter Profile Photo

See this work with Bariscan, the new rising star student from Turkey! Here, we show how even simple changes to task or optimization parameters can lead to distinct geometrical solutions. Most interestingly, this is not completely random. Instead, there are phases of algorithms!!

See this work with Bariscan, the new rising star student from Turkey!

Here, we show how even simple changes to task or optimization parameters can lead to distinct geometrical solutions. Most interestingly, this is not completely random. Instead, there are phases of algorithms!!
David Klindt (@klindt_david) 's Twitter Profile Photo

🧵 New paper! We explore sparse coding, superposition, and the Linear Representation Hypothesis (LRH) through identifiability theory, compressed sensing, and interpretability research. If neural representations intrigue you, read on! 🤓 arxiv.org/abs/2503.01824

Guillermo Bernárdez (@gbg1441) 's Twitter Profile Photo

📢 New Paper Alert! 🚀 Excited to share our latest work, "Ordered Topological Deep Learning: a Network Modeling Case Study", which shows the first state-of-the-art TDL application to a real-world scenario! 📄arxiv.org/pdf/2503.16746 A thread 🧵👇 (1/5)

📢 New Paper Alert! 🚀

Excited to share our latest work, "Ordered Topological Deep Learning: a Network Modeling Case Study", which shows the first state-of-the-art TDL application to a real-world scenario!

📄arxiv.org/pdf/2503.16746

A thread 🧵👇 (1/5)
Martin (@martincar98) 's Twitter Profile Photo

🚨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)

🚨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)