Model techniques map
Techniquestraining objectiveauxiliary loss

specific method · filed under training objective

KL alignment loss

Uses a KL-divergence objective to train or supervise the Index Branch by matching its selection distribution.

Also called KL-divergence loss, KL divergence loss for indexer, KL loss.

sources
3
models
2
labs adopt it
2
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 4

Documented in

Further reading

Picked by hand, not extracted: where to read more, not evidence for anything on this page.

Evidence

4 spans quoted from the sources, strongest treatment first.

train the Index Branch with a KL alignment loss

usedtraining objectivein MiniMax-M3MiniMax

KL loss directly supervises the Index Branch by matching its selection distribution

usedtraining objectivein MiniMax Sparse AttentionMiniMax

Based on p_t,:, we set a KL-divergence loss as the training objective of the indexer

usedtraining objectivein DeepSeek-V3.2DeepSeek

Based on , we set a KL-divergence loss as the training objective of the indexer

usedtraining objectivein DeepSeek-V3.2DeepSeek

Filed alongside

Other methods under training objective :: auxiliary loss.