Unverified50% confidenceFactExact time
The Yandex Music research team replaced more than 15 candidate generators, pre-ranking models, and ranking models in their production environment with a single Transformer model called Sona.
1
Sources
50%
Confidence
Long-term
Relevance
10/5/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTransformer架构最初由Vaswani等人于2017年为NLP设计，后被迁移到视觉（ViT）、音频、蛋白质结构预测等几乎所有AI子领域56% similarUnverifiedThe most common distribution strategy in microcontroller clusters is Pipeline Parallelism, which splits the Transformer model layer by layer52% similarUnverifiedChangeFormer采用层次化Transformer编码器，在LEVIR-CD和DSIFN-CD等基准上取得了SOTA性能52% similarUnverifiedInception AI的Mercury系列模型采用了扩散式Transformer（Diffusion Transformer）架构，可以并行生成多个token52% similarUnverifiedTransformer autoregressive generation is divided into the Prefill stage (compute-intensive, with higher GPU utilization) and the Decode stage (bandwidth-intensive, generating tokens one at a time)51% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/977231API
curl https://kongchang.com/api/v1/knowledge/claims/977231MCP
get_claim(id=977231)