Unverified60% confidenceFactExact time
Rotary Position Embedding (RoPE) was proposed by Su Jianlin in 2021; the position-dependent term in its attention scores depends only on relative position.
2
Sources
60%
Confidence
Long-term
Relevance
7/20/2026
First Seen
Sources
Related Claims
VerifiedRoPE (Rotary Position Embedding) injects positional information into attention computation in the form of a rotation matrix, preserving relative positional relationships across arbitrary sequence lengths.76% similarUnverifiedRoPe（旋转位置编码）由苏剑林等人提出，是一种相对位置编码方案75% similarUnverifiedMany current LLMs use rotary position embeddings (RoPE), rotating the query and key vectors by position so that attention depends on relative distance.74% similarUnverifiedRoPE是一种将位置信息以旋转矩阵形式注入Transformer注意力机制的技术67% similarUnverifiedExtrapolation and interpolation methods for RoPE (Rotary Position Embedding) can extend a model's positional awareness range without retraining.66% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/575504API
curl https://kongchang.com/api/v1/knowledge/claims/575504MCP
get_claim(id=575504)