Unverified50% confidencePredictionExact time
Through hierarchical parallel prediction, NCM can theoretically reduce generation complexity from O(n) to O(log n) or lower, at the cost of potentially losing fine-grained information.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
10/23/2026
First Seen
Valid until: 1/21/2027
Sources
Related Entities
Related Claims
Unverified根据率失真理论，若序列包含O(N)比特相关信息而隐状态只有O(d)比特容量，当N远大于d时必然产生信息丢失75% similarUnverifiedSSMs can reduce computational complexity for processing long sequences to linear level (O(n)).74% similarUnverifiedOpenAI claims that under specific input distributions, the computational complexity of its method can drop below O(N log N).73% similarUnverifiedA domain decomposition strategy can reduce the step complexity from O((L/w)²) to O(L²/(N·w²)), where N is the number of subdomains.72% similarVerifiedThe Fast Fourier Transform reduces the computational complexity of the DFT from the naive O(N²) to O(N log N).72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1088751API
curl https://kongchang.com/api/v1/knowledge/claims/1088751MCP
get_claim(id=1088751)