Unverified50% confidenceFactExact time
The paper proves that for finite-order Markov chains, the minimum memory length is upper-bounded by the Markov order.
1
Sources
50%
Confidence
Long-term
Relevance
10/7/2026
First Seen
Sources
Related Entities
Related Claims
Unverified自回归推理时batch size通常为1，每个token生成只做一次矩阵-向量乘法，算术强度极低，导致memory-bound问题，单用户场景下GPU利用率往往不到10%62% similarUnverifiedROUGE metrics exhibit length bias: models that generate shorter summaries have an advantage in precision, models that generate longer summaries have an advantage in recall, and ROUGE cannot measure factual consistency.61% similarUnverified该神经网络能力上限被Minimax数据锁定，最多只能逼近教师算法水平而无法超越59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/983440API
curl https://kongchang.com/api/v1/knowledge/claims/983440MCP
get_claim(id=983440)