Unverified50% confidenceFactExact time
The core innovation of ERFs is introducing a continuous residual variable for each token and position, embedding the discrete state into a continuous space; the residual evolves deterministically according to a piecewise-defined ODE, and a jump in the discrete state occurs when the residual reaches zero.
1
Sources
50%
Confidence
Long-term
Relevance
10/30/2026
First Seen
Sources
Related Entities
Related Claims
Unverified事件相关电位（ERP）通过对多次刺激响应进行时间锁定叠加平均，使随机背景噪声相互抵消而保留刺激锁定信号，从而提取微弱神经响应64% similarUnverifiedAVALON replaces a posteriori, geometric dense maps (robot-built SLAM) with a priori, semantic sparse structure (human-seeded topological memory); the cost is losing the precise local planning capability brought by continuous metric maps, and the benefit is zero-shot deployment and faster task startup.61% similarUnverifiedGradient Boosting generalizes the idea of AdaBoost to arbitrary differentiable loss functions, with its core operation being that each new model fits the residuals of the previous round.61% similarUnverifiedERS（能量回收系统）在制动时回收动能并在加速时释放，其充放电策略的控制精度直接影响单圈成绩60% similarUnverifiedThe Spaced Repetition System (SRS) is an engineering implementation of the Ebbinghaus forgetting curve, with tools such as Anki dynamically adjusting review intervals through algorithms.59% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1115634API
curl https://kongchang.com/api/v1/knowledge/claims/1115634MCP
get_claim(id=1115634)