Unverified50% confidenceFactExact time
The state recurrence of an SSM is essentially a composition of affine transformations, and the composition of affine transformations is associative, so scan algorithms can be applied.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedState Space Models (SSMs) pull the direction back toward fixed-size recurrent memory, but use a different state structure and update rules.72% similarUnverifiedSelective scan is the core operation of the Mamba family of SSMs, and its discretization parameter Δ, input matrix B and output matrix C all change dynamically with each token.70% 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.68% similarUnverifiedSRM (Spatial Rich Model) is a classical feature extraction framework in the field of digital image forensics, originally designed for steganalysis, which reveals tampering traces by extracting residual statistical features through high-pass filters.68% similarUnverifiedHybrid architectures use attention in layers requiring precise matching and SSMs in layers requiring efficient sequence modeling, in order to strike a balance between inference speed and model capability.67% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1070374API
curl https://kongchang.com/api/v1/knowledge/claims/1070374MCP
get_claim(id=1070374)