Equilibrium Reasoners learn task-conditioned attractors in latent dynamics to support scalable iterative reasoning, raising Sudoku-Extreme accuracy from 2.6% to over 99% via up to 40,000 equivalent layers.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Attractor Models solve for fixed points in transformer embeddings using implicit differentiation to enable stable iterative refinement, delivering better perplexity, accuracy, and efficiency than standard or looped transformers.
citing papers explorer
-
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
Equilibrium Reasoners learn task-conditioned attractors in latent dynamics to support scalable iterative reasoning, raising Sudoku-Extreme accuracy from 2.6% to over 99% via up to 40,000 equivalent layers.
-
Solve the Loop: Attractor Models for Language and Reasoning
Attractor Models solve for fixed points in transformer embeddings using implicit differentiation to enable stable iterative refinement, delivering better perplexity, accuracy, and efficiency than standard or looped transformers.