Unverified50% confidenceFactExact time
The core recurrence of an SSM is h_t = A_t h_{t-1} + B_t x_t, with output y_t = C_t h_t.
1
Sources
50%
Confidence
Long-term
Relevance
11/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedThe continuous-time form of the state space model (SSM) is h'(t)=Ah(t)+Bx(t).73% similarUnverifiedSSM 通过随时间演化的隐藏状态 h_t = A·h_{t-1} + B·x_t 压缩历史信息,输出由 h_t 线性映射得到,单步解码计算量与序列长度无关,显存占用恒定。71% similarUnverifiedThe mathematical roots of SSMs come from linear time-invariant systems in control theory, using matrices A, B, and C to describe how inputs update the hidden state and how the hidden state maps to outputs.61% similarUnverifiedThe continuous form of a state space model is h'(t) = A·h(t) + B·x(t), with output y(t) = C·h(t) + D·x(t); after discretization it processes a sequence of length n with O(n) complexity.61% similarUnverifiedThe reverse SDE of a diffusion process can be expressed as dX_t = [f(X_t,t) - g(t)²∇log p_t(X_t)]dt + g(t)dW̄_t.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1160932API
curl https://kongchang.com/api/v1/knowledge/claims/1160932MCP
get_claim(id=1160932)