Ben Walker
@benjamincwalker.bsky.social
🎓 Machine Learning PhD
🌍 Mathematical Institute, Oxford
📈 Researching Neural Differential Equations & Rough Path Theory
📧 Email: [email protected]
🌐 GitHub: Benjamin-Walker
🌍 Mathematical Institute, Oxford
📈 Researching Neural Differential Equations & Rough Path Theory
📧 Email: [email protected]
🌐 GitHub: Benjamin-Walker
Sonnet-3.7 has me vibe coding for the first time 🎧💻
Never written html, css, or JavaScript before, but I’ve created the website I’ve always wanted, featuring an optional command line interface ✨
BenWalker.co.uk
Never written html, css, or JavaScript before, but I’ve created the website I’ve always wanted, featuring an optional command line interface ✨
BenWalker.co.uk
February 25, 2025 at 1:57 PM
Sonnet-3.7 has me vibe coding for the first time 🎧💻
Never written html, css, or JavaScript before, but I’ve created the website I’ve always wanted, featuring an optional command line interface ✨
BenWalker.co.uk
Never written html, css, or JavaScript before, but I’ve created the website I’ve always wanted, featuring an optional command line interface ✨
BenWalker.co.uk
S4, Mamba, and Transformers need 4 blocks just to compose 12 permutations!
In contrast, using a dense state-transition matrix (IDS4/Linear CDE) or a non-linear state-transition (RNN) allows for state-tracking with only 1 layer.
🧵5/6
In contrast, using a dense state-transition matrix (IDS4/Linear CDE) or a non-linear state-transition (RNN) allows for state-tracking with only 1 layer.
🧵5/6
November 23, 2024 at 9:04 AM
S4, Mamba, and Transformers need 4 blocks just to compose 12 permutations!
In contrast, using a dense state-transition matrix (IDS4/Linear CDE) or a non-linear state-transition (RNN) allows for state-tracking with only 1 layer.
🧵5/6
In contrast, using a dense state-transition matrix (IDS4/Linear CDE) or a non-linear state-transition (RNN) allows for state-tracking with only 1 layer.
🧵5/6