Stream Recursion Model (SRM)

arXiv:2609.28809 · cs.LG · Submitted 2026-09-23 · Read on arXiv

cs.LG

Submitted: 2026-09-23

Updated: 2026-09-23

Project page: http://skylion007.github.io/OpenWebTextCorpus

Terminology

• Alignment — 28× in this paper · explained in 1 episode
• Stream Recursion Model — 24× in this paper
• Cosine Similarity — 23× in this paper · explained in 3 episodes
• Ablation — 19× in this paper · explained in 1 episode
• Transformer — 16× in this paper · explained in 2 episodes
• Interpretability — 13× in this paper · explained in 15 episodes
• Mechanistic interpretability — 6× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Transformer Models — 3× in this paper · explained in 2 episodes
• Core — 2× in this paper · explained in 2 episodes
• Deep Reinforcement Learning — 2× in this paper · explained in 2 episodes
• Hierarchical Reasoning Model — 2× in this paper
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptive Computation Time — 1× in this paper
• Attention Mechanism — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Decoupling — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Tiny Reasoning Models — 1× in this paper

Sources

• A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models
• Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
• Hierarchical Reasoning Model
• Scaling Latent Reasoning via Looped Language Models
• On the Measure of Intelligence
• ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
• Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
• Scaling Exponents Across Parameterizations and Optimizers
• Hierarchical Reasoning Models: Perspectives and Misconceptions
• Less is More: Recursive Reasoning with Tiny Networks

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