Verified65% confidenceFactExact time
Mamba was proposed by Carnegie Mellon University in 2023; based on the State Space Model (SSM), it reduces computational complexity on long-sequence tasks from Transformer's O(n²) to near-linear
3
Sources
65%
Confidence
Long-term
Relevance
7/17/2026
First Seen
Sources
Related Claims
UnverifiedMamba架构由Gu和Dao于2023年提出，其选择性状态空间机制以线性复杂度处理长序列81% similarUnverifiedMamba在2023年12月通过选择性机制和硬件感知的实现取得突破性进展71% similarUnverified2024年涌现了多个线性或近线性复杂度序列模型，包括DeepMind的Griffin、AI21 Labs的Jamba、HGRN2和Stanford的Based59% similarUnverifiedThe DiT architecture was formally proposed by Meta Research in 2023, introducing the Vision Transformer into the denoising process of diffusion models, with computational complexity growing quadratically with sequence length.59% similarUnverifiedLlama系列由Meta AI于2023年以开源形式发布，采用Transformer Decoder架构，通过RoPE和GQA等优化降低推理显存占用58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/547557API
curl https://kongchang.com/api/v1/knowledge/claims/547557MCP
get_claim(id=547557)