Unverified50% confidenceFactExact time
The Isotropic Curvature Model (ICM) explains the effectiveness of Muon from the perspective of curvature: when gradient orthogonalization minimizes a one-step local loss surrogate, Muon's update direction is reasonable.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedAnthropic的理论将ICL解读为贝叶斯推断——模型在上下文中看到示例实际上是在更新其对任务分布的后验概率估计68% similarUnverifiedThe researchers propose the Random-Radius Isotropic Curvature Model (RR-ICM), replacing the fixed radius with a general radial distribution.66% similarUnverifiedSeparating prediction from assignment—having the model only predict loss for each action individually (Noul prediction), then using a deterministic rule (argmin or softmin) to complete the assignment—yielded substantial improvements.65% similarUnverifiedThe effectiveness of model merging relies on an empirical observation: fine-tuned models tend to reside in the same basin of the loss surface, so linearly combining their weights does not lead to performance collapse.62% similarUnverifiedDiffusion models perform better in global consistency but have slower inference speeds, while autoregressive models generate content frame by frame or segment by segment.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1046164API
curl https://kongchang.com/api/v1/knowledge/claims/1046164MCP
get_claim(id=1046164)