single mention · not yet filed
Training-time action-prefix conditioning for asynchronous execution
The sources on this page only mention it in passing.
Related methods
Used for
Methods the sources say this one serves — as a part, a setting, a variant or an enabler.
- Asynchronous inference and executionconfigures
In this work, we follow training RTC [5] and condition action generation on previously committed actions by prefixing them to the noisy action tokens in DiT
Supported by
Methods the sources say are used for this one.
- RoPE positional-index offsetenables it
add an offset to the RoPE positional indices of the noisy action tokens to enable the model to distinguish tokens of noisy actions from those of the clean action prefix
- Shape attention mask for action-prefix conditioningconfigures it
we change the original causal attention mask of the DiT to a -shape attention mask