When Recursive Models Finish Computing
cs.LG, cs.AI, cs.NE
Submitted: 2026-09-22
Updated: 2026-09-22
Code: https://github.com/t-dillon/tdoku
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Deep Equilibrium Models
- Automatic differentiation in machine learning: a survey
- Adaptive Computation Time for Recurrent Neural Networks
- Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
- Less is More: Recursive Reasoning with Tiny Networks
- Fractal basins trap latent reasoning
- Reverse engineering recurrent networks for sentiment classification reveals line attractor dynamics
- Grokking at the Edge of Numerical Stability
- Are Your Reasoning Models Reasoning or Guessing? A Mechanistic Analysis of Hierarchical Reasoning Models
- Sudoku-Bench: Evaluating creative reasoning with Sudoku variants
- RoFormer: Enhanced Transformer with Rotary Position Embedding
- SATNet: Bridging deep learning and logical reasoning using a differentiable satisfiability solver
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks