arXiv Machine Learning
Learning to Compute Is Not Learning to Retain or Reuse in Looped Transformers
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv AI
Oct 9
Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
The paper introduces InfiLoop, a loop-native residual connection designed for looped Transformers to prevent performance degradation as iterations increase. InfiLoop learns which past computations to retain and how much to accept from each new update, combining content-based weighting with learned temporal decay to maintain a running summary of recurrent states. Across extensive reasoning tasks, a 7M-parameter InfiLoop model outperforms existing recursive architectures, achieving 97.9% exact accuracy on Sudoku-Extreme and 13.6% pass@2 on ARC-AGI-2, and continues to improve with test-time looping beyond 20,000 effective steps.
Hugging Face Trending Papers
Oct 8
Scaling to Tens of Thousands of Test-Time Iterations with Loop-Native Attention Residuals
The paper proposes InfiLoop, a loop-native residual connection designed for looped Transformers to prevent performance degradation as iterations increase. InfiLoop learns which past computations to retain and how much to accept from each new update, using content-based weighting and learned temporal decay to maintain a running summary of recurrent states. The approach yields strong results on reasoning tasks, achieving 97.9% exact accuracy on Sudoku-Extreme and 13.6% pass@2 on ARC-AGI-2, and continues to improve with over 20,000 test-time iterations.
arXiv Machine Learning
Sep 4
RecurTrace: Adaptive Latent Reasoning with Loop-Time Memory
RecurTrace introduces adaptive latent reasoning for language models by allowing each looped layer to attend to its own past states and by using a halting head to decide when to stop iterating. This approach overcomes two limitations of prior latent recurrence methods: limited access to earlier computations and a fixed loop count that mismatches input difficulty. In experiments on MathQA, RecurTrace achieves 56.9% accuracy with an average of 2.0 loops, outperforming fixed‑depth baselines and other adaptive methods, and it also improves generation accuracy across a range of model sizes.
arXiv AI
2d ago
Running Fewer Loops Removes Refusal Behaviour in Recurrent-Depth Language Models
arXiv:2610.15218v1 Announce Type: new Abstract: A recurrent-depth language model reuses one block of weights several times in a row. The number of repetitions, which we call loops, is chosen when the...
arXiv AI
Jun 3
PURGE: Projected Unlearning via Retain-Guided Erasure
arXiv:2606. 03808v1 Announce Type: cross Abstract: We propose PURGE, a machine unlearning algorithm built on a simple but an under-exploited observation: continual learning (CL) and machine unlearning (MU) which are fundamentally dual problems.
arXiv Machine Learning
Oct 2
Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop Does
arXiv:2609. 39892v1 Announce Type: new Abstract: Looped Transformers repeatedly apply the same set of Transformer layers, giving them a recurrent architecture for latent computation.