Jordan-RoPE: Non-Semisimple Relative Positional Encoding via Complex Jordan Blocks
Relative positional encodings determine which functions of query-key lag can enter the primitive attention logit. RoPE supplies a rotary phase, while ALiBi supplies an additive distance bias. Motivated by group-theoretic views of linear translation-invariant positional encodings, we study a non-semisimple case in which a complex rotary eigenvalue and a nilpotent response live in the same defective Jordan block. The resulting relative operator generates oscillatory-polynomial features such as $e^{-γd}\cos(ωd)$, $e^{-γd}\sin(ωd)$, $d e^{-γd}\cos(ωd)$, and $d e^{-γd}\sin(ωd)$, for causal lag $d=i-j\geq 0$. Thus the construction realizes a distance-modulated phase basis $d e^{iωd}$, rather than merely adding a separate distance channel to RoPE. We formulate Exact Jordan-RoPE as a non-semisimple one-parameter representation, give its real block form, and specify the contragredient query action required by non-orthogonal positional maps. We also distinguish this exact representation from stabilized variants whose bounded shear improves numerical behavior but breaks the exact group law. Kernel-level diagnostics and a Jordan-friendly synthetic language-model task show that the coupled Jordan basis is useful when the target contains distance-modulated phase interactions. On a small WikiText-103 byte language model, a scaled-exact variant improves over RoPE and direct-sum baselines within the Jordan family, while RoPE+ALiBi remains strongest overall. The evidence is structural rather than a broad performance claim.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
A Circular Argument : Does RoPE need to be Equivariant for Vision?
Rotary Positional Encodings (RoPE) have emerged as a highly effective technique for one-dimensional sequences in Natural Language Processing spurring recent progress towards generalizing RoPE to higher-dimensional data s…
Cameras as Relative Positional Encoding
Transformers are increasingly prevalent for multi-view computer vision tasks, where geometric relationships between viewpoints are critical for 3D perception. To leverage these relationships, multi-view transformers must…
Depth EstimationNovel View SynthesisStereo Depth EstimationDo traveling waves make good positional encodings?
Transformers rely on positional encoding to compensate for the inherent permutation invariance of self-attention. Traditional approaches use absolute sinusoidal embeddings or learned positional vectors, while more recent…
Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models
Rotary Position Embedding (RoPE) is a widely adopted technique for encoding relative positional information in large language models (LLMs). However, when extended to large vision-language models (LVLMs), its variants in…
RayRoPE: Projective Ray Positional Encoding for Multi-view Attention
We study positional encodings for multi-view transformers that process tokens from a set of posed input images, and seek a mechanism that encodes patches uniquely, allows SE(3)-invariant attention with multi-frequency si…
Stereo Depth Estimation