Harrison Ritz

𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗱𝘆𝗻𝗮𝗺𝗶𝗰𝗮𝗹 𝘀𝘆𝘀𝘁𝗲𝗺𝘀 𝗶𝘀 𝗵𝗮𝗿𝗱 But lots of progress being made; this one looks very interesting. arxiv.org/abs/2604.24662

Information bottleneck for learning the phase space of dynamics from high-dimensional experimental data arxiv.org View on Bluesky →

How do time series foundation models forecast unseen dynamical systems? In new experiments, we find that small transformers learn to approximate transfer operators in-context. (1/N) arxiv.org/abs/2602.18679

Transformers for dynamical systems learn transfer operators in-context arxiv.org View on Bluesky →

this is actually a very good article

How LLMs Actually Work 0xkato.xyz View on Bluesky →