Open Models Almanac
Methodstraining objective

single source · training objective

Multiple flow-time samples per action chunk

A training-objective technique for flow-matching action experts that evaluates the flow loss at several sampled noise levels for each action chunk instead of one.1,2 Multiple (noise, target) pairs are drawn per example so the same action chunk and visual-language context supervise several points along the flow trajectory.3

Trade-off More flow samples raise average performance but cost GPU memory, which is why the fine-tuning stage used fewer samples than post-training.4,5

How this definition was written

Summarised by glm-5.3-flash from 1 source; every sentence is checked against the quote it cites.

  1. For each robot action chunk, we evaluate the flow objective at multiple noise levels — MolmoAct2 Action Reasoning Models for Real-World Deployment
  2. vary the number of flow samples per action chunk — MolmoAct2 Action Reasoning Models for Real-World Deployment
  3. each robot sample contributes four points on the same flow trajectory while reusing the same visual-language context — MolmoAct2 Action Reasoning Models for Real-World Deployment
  4. increasing generally improves average performance — MolmoAct2 Action Reasoning Models for Real-World Deployment
  5. mainly due to GPU memory constraints — MolmoAct2 Action Reasoning Models for Real-World Deployment

Also called multiple flow samples.

Filed under training objective