Training-free looped transformers retrofit recurrence to frozen models via damped ODE sub-steps on mid-stack blocks, yielding gains such as +2.64 pp on MMLU-Pro for Qwen3-4B.
A little depth goes a long way: The expressive power of log-depth transformers.CoRR, abs/2503.03961
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
verdicts
UNVERDICTED 6representative citing papers
Looped language models with latent iterative computation and entropy-regularized depth allocation achieve performance matching up to 12B standard LLMs through superior knowledge manipulation.
CCDD defines a joint multimodal diffusion on continuous representation space and discrete token space to combine expressivity with explicit token supervision for diffusion language models.
Denoising Recursion Models train multi-step noise reversal in looped transformers and outperform the prior Tiny Recursion Model on ARC-AGI.
Transformers show limited adaptive depth use on relational reasoning, with clearer evidence after finetuning on the task.
The serial scaling hypothesis formalizes inherently serial problems in complexity theory and demonstrates that diffusion models cannot solve them.
citing papers explorer
-
Scaling Latent Reasoning via Looped Language Models
Looped language models with latent iterative computation and entropy-regularized depth allocation achieve performance matching up to 12B standard LLMs through superior knowledge manipulation.