Key papers

• DeepLoop: Depth Scaling for Looped Transformers (2026)
  Shuzhen Li et al.
  10.06
• Loop the Loopies! (2026)
  Zitian Gao et al.
  10.03
• dRAE: Representation Autoencoder with Hyper-Spherical Codes (2026)
  Tianren Ma et al.
  5.01
• Multiplication Beyond Groups: Stratified Fourier Mechanisms in Transformer Circuits (2026)
  Zitong Andrew Chen et al.
  4.39
• Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning (2026)
  Pranav Sawant et al.
  4.39
• The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought (2026)
  Zhiyuan Li
  4.39
• Targeted Recovery of Weight-Space Mechanisms From Neural Networks (2026)
  Antoine Vigouroux et al.
  4.39
• Local Redundancy: An Information-Theoretic Measure of Plasticity from Synthetic Memorization (2026)
  Jiaxuan Cheng
  4.39
• CAS I: A Geometric Coding Theorem (2026)
  Romie Banerjee
  4.39
• Partially Correlated Verifier Cascades in LLM Harnesses: Concave Log-Odds, Polynomial Reliability, and Blind-Spot Ceilings (2026)
  Jiangang Han
  4.39
• Multi-layer MIMO Relay as Deep Physical Neural Networks: Power Amplifiers as Activation Functions (2026)
  Meng Hua et al.
  4.39
• CRB-Driven Beamforming and Trajectory Optimization for UAV-assisted ISAC System (2026)
  Yi Yang et al.
  4.39
• On the Depth Scalability of Logic Gate Networks (2026)
  Taegun An et al.
  4.39
• Neural Feature Governance: Extending Atom Prevalence (2026)
  Idris Karel Seunda Ekwe et al.
  4.39
• Interior interpretability with attention rollout: contraction and propagation profiles in Transformers (2026)
  Umberto Biccari et al.
  4.39
• CausalGate: Causal Importance Distillation for Transformer Module Pruning (2026)
  Kiran Nair et al.
  4.39
• Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientist (2026)
  Mohsen Aliabadi et al.
  4.39
• Breaking the Data Barrier in Learning Symbolic Computation: A Case Study on Variable Ordering Suggestion for Cylindrical Algebraic Decomposition (2026)
  Rui-Juan Jing et al.
  3.92
• A Structural Interpretation of GELU and Threshold-Transmission Activations via the First-Order Loss Function (2026)
  Roberto Rossi
  3.51
• Emergent Sparsity in Frozen Random CNN Feature Extractors for Deep Reinforcement Learning (2026)
  Scott M. Norton
  2.00
• Shared Symbolic Backbones for Physically Consistent Multi-Output Symbolic Regression (2026)
  Manuel Rodriguez
  2.00
• The Sparsity Ceiling: Where Spiking Networks Can and Cannot Trade Activity for Energy (2026)
  Zeyu Wang
  2.00
• An Empirical Audit of Input Encoders for Multi-Channel Signal Transformers (2026)
  Ossi Lehtinen
  1.94
• Learning to Decode: Graph Attention Network-Gated Recurrent Unit as Channel Decoder (2026)
  Lixin Qian et al.
  1.94
• Towards Verifiable Transformers: Solver-Checkable Circuit Explanations (2026)
  Neel Somani
  1.89
• Vector-Valued Reproducing Kernel Banach Spaces for Neural Networks and Operators (2025)
  Sven Dummer et al.
  1.44
• Dense Local Dependencies Induce Attention-Logit Explosion and Training Instability During Long-Sequence Transformer Training (2025)
  Suvadeep Hajra
  1.22