ambiguous · filed under post-training
Three-stage Thinker post-training strategy
A three-stage post-training strategy for the Thinker intended to preserve capabilities across modalities; the evidence does not specify the stages.
Also called three-stage strategy for the Thinker.
- source
- 1
- model
- 1
- 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.
The post-training phase employs a three-stage strategy for the Thinker, designed to preserve the model’s capabilities across all modalities without degradation
usedpost trainingin Qwen3.5-OmniQwen
Filed alongside
Other methods under post-training.
Scalable RL at Agent ScaleReinforcement learning for low-pass-rate tasksScalable reinforcement learning post-trainingSFT followed by RL and on-policy distillationExtended post-trainingJoint SFT and RLPost-training on diverse domainsPost-training optimizationThree-stage post-training with multi-teacher on-policy distillation