Disordered Systems & Neural Networks

Papers

• Harnessing cortical geometry, wiring, and function as inductive biases for recurrent neural networks (2026)
  Mo Shakiba et al.
  5.49
• Neuron Level Analysis of Large Language Model in Legal Domain Reasoning (2026)
  Eri Onami et al.
  5.49
• The Weight Norm Sets the Grokking Timescale: A Causal Delay Law (2026)
  Truong Xuan Khanh et al.
  4.39
• Beyond Layer Importance in Layer-wise Sparsity: An Inter-Layer Perturbation-Absorption Perspective (2026)
  Tao Jing et al.
  4.39
• Analyzing Visual Aircraft Representations with Sparse Autoencoders (2026)
  Deepshik Sharma
  4.39
• Sobolev Approximation by Fixed-Size Neural Networks with Arbitrary Accuracy (2026)
  Baicheng Li et al.
  4.39
• Natively Unlearnable Large Language Models (2026)
  Gaurav R. Ghosal et al.
  3.51
• Decompose Sparsely Where You Should, Absorb Densely Where You Should No (2026)
  Ruixuan Deng et al.
  3.51
• Can Neural Networks Achieve Optimal Computational-statistical Tradeoff? An Analysis on Single-Index Model (2026)
  Siyu Chen et al.
  3.51
• Fantastic Pretraining Optimizers and Where to Find Them II: Hyperball Optimization (2026)
  Kaiyue Wen et al.
  3.51
• Convergence rates for gradient descent in the training of overparameterized artificial neural networks with piecewise affine activation (2026)
  Arnulf Jentzen et al.
  2.00
• The Frequency Confound in Language-Model Surprisal and Metaphor Novelty (2026)
  Omar Momen et al.
  2.00
• The Symmetries of Three-Layer ReLU Networks (2026)
  Johanna Marie Gegenfurtner et al.
  2.00
• Semi-Supervised Noise Adaptation: Transferring Knowledge from Noise Domain (2026)
  Yuan Yao et al.
  2.00
• Knockoffs-based False Discovery Rate Control and Simplification for Deep Neural Networks (2026)
  Wenyu Liao et al.
  2.00
• Depth-Attention: Cross-Layer Value Mixing for Language Models (2026)
  Boyi Zeng et al.
  2.00
• HAARES Half-Split Residual Basis Routing for Deep Transformers (2026)
  Kehan Wang
  2.00
• Overcoming Rank Collapse in Feedback Alignment (2026)
  Gauthier Boeshertz et al.
  2.00
• Unlearning What Matters: Token-level Attribution For Precise Language Model Unlearning (2026)
  Jiawei Wu, Doudou Zhou
  2.00
• Spectral Architecture Search for Neural Network Models (2025)
  Gianluca Peri et al.
  1.22