Pinned Tweet
Introducing gyaradax 🐉: A JAX solver for local flux-tube gyrokinetics with custom CUDA kernels for acceleration.
This entire code was vibecoded by @ggalletti_ and me in a month.
Validated against GKW (CPU-only Fortran code) with 10x speedups. Details and code in the replies.
Eric Volkmann retweeted
A great 2nd place finish at the intense Tokyo AI × OpenAI 100-Hour Game Builder Challenge.
@r_etx, @e_volkmann and I built autoV for the hackathon.
we built an AI agent and a platform to generate editable, real-time VFX, rather than just producing a finished asset. VFX creation should be fast and accessible while still giving the artist control when they need it.
A special thanks as well to the organizers, @TokyoAI_JP
the judges @jtwald , @peacej , @shunsuke00 , @rpereyda , Teddy Cross @playco , Tyler Ryu, and the sponsors, @OpenAI and @vercel .
#GameDev #GenerativeAI #VFX
Replying to @e_volkmann @ggalletti_
JAX’s native AD enables differentiable physics out of the box.
To showcase a use case, we use gradient-based optimizers to solve inverse problems, such as recovering temperature gradients (R/LT) and performing exact sensitivity analysis on the growth rates.
Replying to @e_volkmann @ggalletti_
Paper: arxiv.org/abs/2604.06085
Code: github.com/gerkone/gyaradax
Preparing for the poster session at #ICML2025
Drop by at W-504 to discuss GINNs: Geometry-Informed Neural Networks.
GINNs lie at the Intersection of Geometry, neural shapes and generative modelling.
Looking forward to the discussion! 😃
Alena and I will be presenting our poster today at #NeurIPS2024 in the afternoon session. East hall, #3710
Excited to discuss and answer questions.
Can we learn dynamical systems from short, noisy #fMRI data? Building on advanced frameworks for dynamical systems reconstruction (DSR), we present a novel scalable SSM DSR algorithm for fMRI. With Eric Volkmann, Alena Braendle & #DurstewitzLab Explore: arxiv.org/abs/2411.02949
4
146
Eric Volkmann retweeted
Geometry-Informed Neural Networks are evolving! Beyond faster training and improved shapes, GINNs surprised us with an emergent property – a structured latent space. 🧵
Huge progress by @artuursberzins @AndyRadler @e_volkmann on Geometry-Informed Neural Networks (GINNs)! Faster training, better shapes, and surprising insights from enforcing diversity.
📜: arxiv.org/abs/2402.14009
🖥️: arturs-berzins.github.io/GIN…









