Verified75% confidenceFactExact time
State space models represented by Mamba compress historical information by maintaining a fixed-size hidden state, with both time and space complexity of O(1) during inference.
3
Sources
75%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
VerifiedMamba 等基于状态空间模型（SSM）的架构以线性复杂度实现序列建模，更适合实时推理80% similarVerifiedState space models (SSMs) such as Mamba abandon the attention mechanism and use recurrent structures to achieve linear time complexity sequence modeling.77% similarUnverifiedThe Mamba state space model was proposed by Albert Gu and Tri Dao in 2023, with both computational complexity and memory usage at O(1) during inference77% similarUnverifiedLinear-complexity models such as Mamba serve as a new architectural reference point targeting the O(n²) bottleneck71% similarUnverifiedDuring inference, Mamba can run in pure recurrent mode with constant memory usage.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/899468API
curl https://kongchang.com/api/v1/knowledge/claims/899468MCP
get_claim(id=899468)