Joined January 2012
- Tweets 151
- Following 692
- Followers 616
- Likes 1,183
22 Photos and videos
Pinned Tweet
Jan 30
New open source: cuthbert 🐛
State space models with all the hotness: (temporally) parallelisable, JAX, Kalman, SMC
1
17
79
10,634
Jun 11
The World Cup starts soon, I wrote a model using cuthbert to predict the games and @ryantjx53 built an awesome frontend 🐛⚽️
Check out cuthberto-carlos ryantjx.github.io/cuthberto-…
1
8
664
Sam Duffield retweeted
May 29
graphic design remains my passion
sites.google.com/view/newcas…
1
5
31
2,944
May 28
Co-organising a workshop: Non-Equilibrium Sampling: Diffusions · Flows · Particles
September, Newcastle
Come join the fun!
sites.google.com/view/newcas…
3
85
Sam Duffield retweeted
May 28
1
4
17
4,697
Sam Duffield retweeted
Fixed point iterations for parallelizing nonlinear dynamics is all the rage:
- Newton for RNNs
- Picard for diffusion models
- Jacobi for parallel decode of LLMs
But how do these techniques relate, and when should you use them?
We show you how in our new paper 🧵
6
27
172
20,394
Sam Duffield retweeted
May 1
I am still thinking about that key equation too!
1
5
273
Apr 27
It was super fun to present my SDE decomposition at the @iclr_conf DeLTa workshop
And thanks for stopping by @wellingmax @mmbronstein, really enjoyed chatting and lots to think about!
3
3
30
3,781
Apr 27
1
1
257
Sam Duffield retweeted
At @iclr_conf in Rio? Join us for the Normal Silicon Social on Sunday, April 26 from 6:30 to 8:30 PM at the Copacabana Palace.
Request an invite: luma.com/3ioi64wv
#ICLR2026
3
6
689
Sam Duffield retweeted
Apr 25
Did @wellingmax’s keynote at #iclr2026 leave you wanting more stochastic thermodynamics and generative AI?
Come join Max and me at poster #1023 in Pavilion 3 in the afternoon to chat about how we can learn escorted protocols for multistate free-energy estimation!
1
8
35
5,570
Sam Duffield retweeted
Normal Computing is sponsoring @iclr_conf 2026 in Rio de Janeiro.
Our research team will be on-site presenting papers spanning thermodynamic computing, Normal's physics-based computing architecture, and the AI methods underpinning Normal EDA, our platform for silicon engineering.
Come talk to the researchers behind the work. We'll share a preview of what we're launching live at the conference. Follow along for real-time updates in the ICLR app.
Meet us at the booth:
Thursday, April 23 – Saturday, April 25
9:30 AM – 5:30 PM daily
2
6
762
Apr 21
I'll be at ICLR this week 🇧🇷 presenting my complete SDE decomposition at the DeLTA workshop on Monday.
Reach out if you want to meet!
6
128
Sam Duffield retweeted
Apr 9
cuthbert is turning into a really awesome tool that's made our experience in writing dynestyx (github.com/BasisResearch/dyn…) much more pleasant! Super happy to be seeing symbiosis between the two!
Apr 9
The ensemble Kalman filter has been added to cuthbert by @DanWaxmanML @BasisOrg 🔥
The EnKF is one of those algorithms that "just works" - oftentimes in settings it has no right to
github.com/state-space-model…
1
138
Apr 9
The ensemble Kalman filter has been added to cuthbert by @DanWaxmanML @BasisOrg 🔥
The EnKF is one of those algorithms that "just works" - oftentimes in settings it has no right to
github.com/state-space-model…
1
3
267
Apr 9
In this highly nonlinear example it's more accurate and faster than both extended and particle filters.
state-space-models.github.io…
1
77
Apr 9
There's a load of fun examples in the cuthbert docs and we're always looking to add more! 🐛
state-space-models.github.io…
1
56