Unverified50% confidenceFactExact time
Pistis's training pipeline is divided into two stages: the first stage is large-scale multimodal supervised fine-tuning (SFT), and the second stage is Interleaved Distillation and Reinforcement Learning (IDRL).
1
Sources
50%
Confidence
Long-term
Relevance
9/25/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTRACER employs a two-stage training process: the first stage performs supervised fine-tuning (SFT) on real user conversations, and the second stage introduces multi-turn reinforcement learning (RL).74% similarVerifiedLarge model training goes through three core stages: pre-training, supervised fine-tuning (SFT), and preference alignment.73% similarUnverified继续预训练（CPT）是在通用基座模型上用领域语料进行额外的无监督训练，让模型吸收领域知识68% similarVerified从预训练检查点到可商用产品需经历监督式指令微调（SFT）和基于人类反馈的强化学习（RLHF）两个后训练阶段68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/948994API
curl https://kongchang.com/api/v1/knowledge/claims/948994MCP
get_claim(id=948994)