Spherical Brownian Diffusion for Language Modeling
Corrupts token embeddings with Brownian motion on a sphere and trains a model to recover clean tokens. Controlled comparisons separate the effect of the corruption process from the sampling method on Sudoku, math problems and text generation.
First public: · Added to this list: November 2, 2026
Explore this approach
Alternative generation methods — Change how intermediate steps are generated, revised, or searched—for example, by refining several steps in parallel. Some produce written chains of thought.
Continuous-state reasoning — Use vectors—lists of numbers—to carry intermediate reasoning from one step to the next, instead of selecting a text token at every step. Some methods use the model's hidden states; others combine several candidate token representations.
Analysis and evaluation — Measure how well these methods work, investigate what their internal computation does, and identify where they fail. This includes experiments, studies of model internals, and mathematical results.