Spherical Flows for Categorical Data Paper Lands NeurIPS 2026 Spotlight
LucaAmb · x · 2026-09-26
Researchers announced their paper on spherical flows for categorical data was accepted to NeurIPS 2026 as a spotlight. An early version was previously presented at a diffusion-LLM community event, and the paper has since grown substantially.
More from Research
- Zero-data self-play pretraining: LM learns to generate its own training data from random init — inductionheads · 2026-09-26
- How much watermark signal fits in AI text? A developer works the math end to end — OtherwisePush6424 · 2026-09-26
- LISA: Prompting LLMs to Build Interpretable Style Embeddings and a Stylometry Dataset — deliprao · 2026-09-26
- BindCraft 2 runs protein design on consumer GPUs at just 2 cents per trajectory — iskander · 2026-09-26
- Yoav Goldberg: Buckmaster sees AI agents as simply a way to scale test-time compute — yoavgo · 2026-09-26
- Japan's Tooth-Regrowth Drug Blocking USAG-1 Completes Phase I, Kids Trial Next — bumpthebass · 2026-09-26