Expanding Flow Maps can insert tokens or nodes while denoising
KevinKaichuang · x · 2026-07-28
Expanding Flow Maps let flows grow the output size while denoising
The post introduces Expanding Flow Maps (EFMs), a new family of flow-based generative models that can generate outputs with more dimensions than the input.
Key points:
- Existing flow models usually assume fixed input and output dimensions or fixed sequence length.
- EFMs add an expand operator that inserts new coordinates or tokens conditioned on the current state.
- A transport map then denoises and moves the expanded state forward.
- The framework also extends to the discrete simplex, enabling variable-size graph generation and variable-length sequence generation.
- The authors frame this as useful for cases where output size itself should be a learned, controllable variable, with applications in biology and chemistry.
Related event: New Flow Models Enable Dynamic Dimension Expansion During Denoising(2 posts)→
More from Embodied
- GEFIT uses a RealSense D555 stereo camera for robotic pick-and-place — chrismatthieu · 2026-07-28
- Does an AI agent really need dedicated hardware, or just better software? — Jayden_Wong0211 · 2026-07-28
- SolidWorks build turns seven actuators into a 7-DOF humanoid robot arm — philfung · 2026-07-28
- Chelsea Finn says robotics is bottlenecked by rollout cost and memory — chris_j_paxton · 2026-07-28
- A cracked pair of Ray-Ban glasses becomes a joke about smart-glasses backlash — AIFlow_ML · 2026-07-28
- Physical AI could make industrial robots easier to deploy — Responsible-Grass452 · 2026-07-28