flowl: a probabilistic programming language built on optimal transport, not distributions
burny_tech · x · 2026-11-02
tsuname shares flowl, a fun side project: a probabilistic programming language based on optimal transport, plus a pointer to a Princeton review bridging control theory, inference and thermodynamics.
- Instead of parametric distributions and likelihoods, flowl uses particle-based Clouds linked by geometric constraints (drift, covers, warp)
- Inference is Wasserstein gradient flow: the solver relaxes a spring network to equilibrium
- Built on JAX + OTT-JAX; the README quick start shows a hierarchical model example
- Author's hunch: distributions may be the wrong abstraction for many modeling tasks
More from Research
- Essay: whether AI ends or elevates human math depends on two models of progress — Dr_Atoosa · 2026-11-02
- Qwen 27B orchestrates SAM 3 per tile: one H200 serves 12 patients in medical imaging — MaziyarPanahi · 2026-11-02
- Rentosertib: a 7-year quest for an aging drug worth 110 million human lifetimes — rand_longevity · 2026-11-02
- GeBNLP 2026 goes virtual Nov 9 at AACL with keynotes from Savoldi and Gautam — debora_nozza · 2026-11-02
- From-scratch 128x128 rectified-flow model draws newsprint faces on CPU in 0.27s, MIT licensed — rustydustyshckleford · 2026-11-02
- Berkeley's Evolving Agent Teams beats production FlashInfer by 1.2x on CUDA kernels from scratch — berkeley_ai · 2026-11-02