arXiv Computation and Language By Abraham Chachamovits

Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance

Read the original on arXiv Computation and Language →

The paper introduces a bounded spectral framework to analyze rotary attention in transformer language models, focusing on phase alignment, hidden‑state continuity, and semantic drift. It identifies ordered hidden‑state sequences as suitable domains for spectral decomposition, derives the Rotary Position Embedding (RoPE) attention score as a sum of magnitude‑weighted cosine terms, and proves a local stability lemma linking bounded phase displacement to pre‑softmax score degradation. By defining complex modal coordinates and a weighted coherence functional, the work distinguishes representational continuity from execution‑boundary admissibility, offering a theoretical program for when spectral structure explains continuity and when external governance is required.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv AI
1d ago

Time-Frequency Geometric Cross-Attention for Chunked Vision-Language-Action Models

The paper introduces Time‑Frequency Geometric Cross‑Attention (TFGCA), a module that enhances vision‑language‑action models by decomposing action chunks into time‑frequency tokens using a learnable wavelet transform. TFGCA fuses dot‑product similarity with wedge‑product magnitude to better capture both frequency‑based smooth trends and cross‑phase orthogonal motion structures. When added to a pretrained VLA model, it yields significant performance gains across in‑distribution and out‑of‑distribution benchmarks, including a 28.5‑point improvement under RoboTwin domain randomization and an 11.67‑point increase on real‑robot AgiBot A2 tasks.

By Shengye Dong, Haochen Niu, Hao Liu, Peiwen Lin, Chuang Wang, Shanmin Pang