Intuition vectors

arXiv:2609.32619 · cs.LG, cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.LG, cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Project page: https://da-fr.github.io/arc-prize-2024/the_architects.pdf

Terminology

• Accuracy — 22× in this paper · explained in 1 episode
• Benchmark — 11× in this paper · explained in 2 episodes
• Transformer — 9× in this paper · explained in 2 episodes
• Alignment — 4× in this paper · explained in 1 episode
• Latent Space — 3× in this paper · explained in 7 episodes
• World Model — 3× in this paper · explained in 7 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Cosine Similarity — 2× in this paper · explained in 3 episodes
• Embeddings — 2× in this paper · explained in 2 episodes
• Generative Model — 2× in this paper · explained in 2 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Few-Shot Learning — 1× in this paper · explained in 4 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Modular Architecture — 1× in this paper · explained in 4 episodes
• Representation Learning — 1× in this paper · explained in 2 episodes
• Self-Distillation — 1× in this paper · explained in 7 episodes
• Self-Supervised Learning — 1× in this paper · explained in 8 episodes
• Self-Supervised Learning (SSL) — 1× in this paper · explained in 4 episodes
• Sparsity — 1× in this paper · explained in 4 episodes

Sources

• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
• Refusal in Language Models Is Mediated by a Single Direction
• ARC-AGI-2: A New Challenge for Frontier AI Reasoning Systems
• On the Measure of Intelligence
• Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds
• Into the Rabbit Hull: From Task-Relevant Concepts in DINO to Minkowski Geometry
• Revisiting the Platonic Representation Hypothesis: An Aristotelian View
• Adapting Self-Supervised Representations as a Latent Space for Efficient Generation
• Discovering Interpretable Directions in the Semantic Latent Space of Diffusion Models
• Less is More: Recursive Reasoning with Tiny Networks
• Interpreting Physics in Video World Models
• Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
• Combining Induction and Transduction for Abstract Reasoning
• Searching Latent Program Spaces
• ARC-GEN: A Mimetic Procedural Benchmark Generator for the Abstraction and Reasoning Corpus
• The Linear Representation Hypothesis and the Geometry of Large Language Models
• Support-Set Context Matters for Bongard Problems
• Diffusion Transformers with Representation Autoencoders
• DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning

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