A Tilted Bowl Is Not a Slippery Slope: Compressing Looped Models
cs.LG, cs.CL
Submitted: 2026-09-30
Updated: 2026-09-30
Terminology
Sources
- PonderNet: Learning to Ponder
- Training Verifiers to Solve Math Word Problems
- Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
- LoopQ: Quantization for Recursive Transformers
- Adaptive Computation Time for Recurrent Neural Networks
- Quantizing Recursive Reasoning Models
- What Survives When You Compress a Recursive Reasoner for the Edge?
- Less is More: Recursive Reasoning with Tiny Networks
- Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
- Quantization Hurts Reasoning? An Empirical Study on Quantized Reasoning Models
- Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
- Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
- A White Paper on Neural Network Quantization
- Microscaling Data Formats for Deep Learning
- Probabilistic Tiny Recursive Model
- Hierarchical Reasoning Model
- Scaling Latent Reasoning via Looped Language Models
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