[KongchangAI]
Unverified50% confidenceFactExact time

Gaussian Splatting EBM represents the entire corpus as a set of Gaussian splats in embedding space, where each splat is defined by three parameters: position (mu), sharpness (alpha), and weight (kappa), and the energy function is the negative of the logsumexp over the nearest k splats.

1
Sources
50%
Confidence
Long-term
Relevance
10/26/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1099011
API
curl https://kongchang.com/api/v1/knowledge/claims/1099011
MCP
get_claim(id=1099011)