Unverified50% confidenceFactExact time
Axion 1.0's training recipe has only three stages: two lightweight SFT stages and one reinforcement learning stage.
1
Sources
50%
Confidence
Long-term
Relevance
11/4/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedPistis'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).72% similarVerifiedLarge model training goes through three core stages: pre-training, supervised fine-tuning (SFT), and preference alignment.71% similarUnverifiedAxion 1.0's training pipeline does not include dedicated mid-training, direct preference optimization (DPO) or on-policy distillation (OPD).71% similarVerifiedThe three-stage alignment training paradigm of SFT–reward model–RLHF was first systematically proposed by OpenAI in the InstructGPT paper.68% similarUnverifiedOn BrowseComp-Plus, attribution-guided SFT matches the effect of full-turn exact-context SFT using only about 30% of the training tokens.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1135493API
curl https://kongchang.com/api/v1/knowledge/claims/1135493MCP
get_claim(id=1135493)