Unverified50% confidenceFactExact time
SSM inference complexity is linear in sequence length, and the state size is constant.
1
Sources
50%
Confidence
Long-term
Relevance
11/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCompared with the quadratic complexity of Transformer, SSM has the advantages of linear time complexity and constant inference memory in long-sequence modeling.80% similarUnverifiedState space models (SSMs) describe the evolution of a sequence via recurrence over a hidden state, and their continuous-time form can be discretized into a linear recurrence, handling long sequences with linear complexity.76% similarUnverifiedMamba2 maintains linear time complexity and constant state size, and therefore has a theoretical advantage in long-sequence scenarios.70% similarVerifiedMamba 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68% similarUnverifiedState space models (SSMs) have O(1) memory footprint and computation during inference, whereas the KV cache of Transformers grows linearly with sequence length.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1160941API
curl https://kongchang.com/api/v1/knowledge/claims/1160941MCP
get_claim(id=1160941)