Model techniques map
Techniquesdata curationdata mixture & curriculum

general family · filed under data curation

Sample Mixer

Uses four mechanisms to fill a specified training distribution for stable asynchronous mixed-task reinforcement learning.

source
1
models
2
lab adopt it
1
strongest
core

How sources treat it

One count per evidence span, weakest treatment to strongest.

core 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we implement the Sample Mixer, with four mechanisms filling the specified training distribution

coreunclearin MiMo-V2.6 RL and OPD infrastructureXiaomi

Filed alongside

Other methods under data curation :: data mixture & curriculum.