specific method · filed under post-training
Self-correction cold start
A cold-start approach in which the model reflects on and rewrites its own misaligned turns into grounded next steps.
Also called Cold start from self-correction.
- sources
- 2
- models
- 2
- lab adopt it
- 1
- strongest
- used
How sources treat it
One count per evidence span, weakest treatment to strongest.
used 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
Cold start from self-correction — the model reflects on and rewrites its own misaligned turns into grounded next steps.
usedpost trainingin MiMo-V2.6-Pro-RLXiaomi
Cold start from self-correction — the model reflects on and rewrites its own misaligned turns into grounded next steps.
usedpost trainingin MiMo-V2.6-Flash-RLXiaomi
Filed alongside
Other methods under post-training :: supervised fine-tuning.
Supervised fine-tuningFine-tuningLight SFT on teacher-distribution dataLoRA fine-tuningRejection samplingSFT bootstrapping with synthetic dataAdversarial fine-tuningAutoregressive fine-tuningCold-started SFT modelEvaluation-based early stoppingFine-tuning with demographically balanced datasetsFrozen-network warmup for new special tokensInstruction hierarchy trainingInstruction-following fine-tuningLightweight speaker fine-tuningPrompt-based cold start for tool useReasoning-data system promptSafety training to an internal specificationSFT checkpoint for RL researchSFT on MiMo-generated task dataSpecialist-model trainingSupervised fine-tuning at 256k sequence lengthToken-budget-based SFT data blending