Towards Looped Models Done Right, Part II: Rethinking at Fixed Points
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Code: https://github.com/ifm-ai/xllm-loop
Sources
- Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
- Loop the Loopies!
- SMELT: Scaling Laws for Compute-Matched MoE Looped Transformers
- Scaling Latent Reasoning via Looped Language Models
- Stabilizing Recurrent Dynamics for Test-Time Scalable Latent Reasoning in Looped Language Models
- Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
- Depth-adaptive Inference of Looped Language Models via Continuous Depth Batching
- A Mechanistic Analysis of Looped Reasoning Language Models
- On Training Implicit Models
- Hierarchical Reasoning Model
- Parcae: Scaling Laws For Stable Looped Language Models
- Multiscale Deep Equilibrium Models
- KV Prediction for Improved Time to First Token
- FitNets: Hints for Thin Deep Nets
- Learning values across many orders of magnitude
- LLaMA: Open and Efficient Foundation Language Models
- Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
- Pointer Sentinel Mixture Models
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
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: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks