Model techniques map
Techniquestraining objectivemulti-token prediction objective

specific method · filed under training objective

Multi-Token Prediction

An auxiliary training objective that predicts multiple future tokens to provide richer training signals.

Also called Multi-Token Prediction (MTP), Multiple-Token Prediction, MTP, Multi-token prediction training.

sources
3
models
4
labs adopt it
3
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 5

Documented in

Evidence

5 spans quoted from the sources, strongest treatment first.

We incorporate Multiple-Token Prediction as an additional training objective

usedtraining objectivein MiMo-7B-BaseXiaomi

The MTP layers of MiMo-7B is tuned during pretraining and SFT and freezed during RL.

usedtraining objectivein MiMo-7B-BaseXiaomi

We support MTP in vLLM and enhance the robustness of the inference engine in the RL system.

usedmodel architecturein MiMo-7B seriesXiaomi

MTP: 1 layer, trained with multi-steps

usedunclearin Qwen3.8-Flash-NextQwen

predicting multiple future tokens provides richer training signals and encourages models to plan several steps ahead

usedtraining objectivein NVIDIA Nemotron 3 Super and UltraNVIDIA

Filed alongside

Other methods under training objective :: multi-token prediction objective.