Rotors: Lightweight Geometric Recurrence for Edge Intelligence

Applications of AI on edge devices are hampered by hardware limitations. To overcome these limitations, we re-frame sequence modeling through rotations on cooperating $SO(D)$ manifolds. Applied to sequence decoding, this enables stable recurrence over extended contexts that match standard Transformer baselines in perplexity with only $O(1)$ memory complexity at inference. In bypassing the context bottleneck of Transformers, Rotors offer a mathematically robust, deterministic and performant paradigm for real-time edge intelligence.