Papers

• The Geometry of Semantic Space: A Continuous Geometric Framework for the Transformer Architecture (2026)
  Zhihua Liang
  7.85
• From Self-Attention to Connection Laplacian: A Unified Operator View of Transformers (2026)
  Binbin Lin et al.
  3.51
• T^2MLR: Transformer with Temporal Middle-Layer Recurrence (2026)
  Ziyang Cai et al.
  3.51
• Feature Entanglement-based Quantum Multimodal Fusion Neural Network (2026)
  Yu Wu, Qianli Zhou, Jie Geng, et al.
  1.67
• Understanding Infonce: Transition Probability Matrix Induced Feature Clustering (2025)
  Ge Cheng, Shuo Wang, Yun Zhang
  1.28
• Hyperbolic Multimodal Representation Learning For Biological Taxonomies (2025)
  Zeming Gong, Chuanqi Tang, Xiaoliang Huo, et al.
  1.28
• Learning-based Hashing For ANN Search: Foundations And Early Advances (2025)
  Sean Moran
  1.28
• Tdhook: A Lightweight Framework For Interpretability (2025)
  Yoann Poupart
  1.28
• Unified Sparse-matrix Representations For Diverse Neural Architectures (2025)
  Yuzhou Zhu
  1.28
• Sg-blend: Learning An Interpolation Between Improved Swish And GELU For Robust Neural Representations (2025)
  Gaurav Sarkar, Jay Gala, Subarna Tripathi
  1.22
• CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers (2025)
  Yoshihiro Yamada
  1.17