1 citations · 1 across the 5 of their papers we have counts for
7 papers
HySPE: Positional Encoding via Symplectic Dual Shears
Zhongping Ji
We introduce Hyperbolic Symplectic Positional Encoding (HySPE), grounding positional attention in non-compact symplectic transformations. While canonical Rotary Position Embedding…
Minkowski Attractor Networks: Closed-Form Hyperbolic Flows for Visual Representations
Zhongping Ji
Geometric representation learning predominantly scaffolds representations onto flat Euclidean subspaces or compact product tori (). However, flat manifolds possess va…
Ananke: Contractive Torus Attractor Networks
Zhongping Ji
We introduce Ananke, a representation-learning framework that scaffolds latent representations onto a structured product-torus prior, and its flagship visual backbone realization,…
IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotations for LLM KV Cache Compression
Zhongping Ji
Orthogonal feature decorrelation is effective for low-bit online vector quantization, but dense random orthogonal transforms incur prohibitive storage and compute. RotorQu…
CliffordNet: All You Need is Geometric Algebra
Zhongping Ji
Modern computer vision architectures, from CNNs to Transformers, predominantly rely on the stacking of heuristic modules: spatial mixers (Attention/Conv) followed by channel mixers…
RiemannFormer: A Framework for Attention in Curved Spaces
Zhongping Ji
This research endeavors to offer insights into unlocking the further potential of transformer-based architectures. One of the primary motivations is to offer a geometric interpreta…
MHS-VM: Multi-Head Scanning in Parallel Subspaces for Vision Mamba
Zhongping Ji
Recently, State Space Models (SSMs), with Mamba as a prime example, have shown great promise for long-range dependency modeling with linear complexity. Then, Vision Mamba and the s…