Learn Your Own Thoughts: Abstract Token Curriculum
cs.LG, cs.AI, cs.CL, stat.ML
Submitted: 2026-09-17
Updated: 2026-09-23
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Reasoning Beyond Language: A Comprehensive Survey on Latent Chain-of-Thought Reasoning
- From Explicit CoT to Implicit CoT: Learning to Internalize CoT Step by Step
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Training Large Language Models to Reason in a Continuous Latent Space
- Less is More: Recursive Reasoning with Tiny Networks
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
- The Expressive Power of Transformers with Chain of Thought
- Let Me Think! A Long Chain-of-Thought Can Be Worth Exponentially Many Short Ones
- Parcae: Scaling Laws For Stable Looped Language Models
- Reasoning with Latent Thoughts: On the Power of Looped Transformers
- How Much Is One Recurrence Worth? Iso-Depth Scaling Laws for Looped Language Models
- Hierarchical Reasoning Model
- Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
- Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
- Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought
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