Model techniques map
Techniquespost-trainingreinforcement learning algorithm

specific method · filed under post-training

Keep Candidate-Set Replay

Recording each token's rollout candidate set and renormalizing training log-probabilities within that set.

Also called candidate-set replay.

source
1
models
2
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

we record each token’s candidate set during rollout and renormalize the training log-probabilities within it, matching the sampler’s normalization.

usedsoftware implementationin MiMo-V2.6Xiaomi

Filed alongside

Other methods under post-training :: reinforcement learning algorithm.