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.
Two-scale latent dynamics for recurrent-depth transformers.arXiv preprint arXiv:2509.23314
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
fields
cs.LG 4years
2026 4verdicts
UNVERDICTED 4representative citing papers
Looped SSMs with shared parameters across depth match or exceed standard SSMs with more parameters on time series classification, with additional gains from input reshaping techniques.
Looped LLMs converge to distinct cyclic fixed points per layer, repeating feedforward-style inference stages across recurrences.
Hyperloop Transformers outperform standard and mHC Transformers with roughly 50% fewer parameters by looping a middle block of layers and applying hyper-connections only after each loop.
citing papers explorer
-
Training-Free Looped Transformers
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.
-
Looped SSMs: Depth-Recurrence and Input Reshaping for Time Series Classification
Looped SSMs with shared parameters across depth match or exceed standard SSMs with more parameters on time series classification, with additional gains from input reshaping techniques.
-
A Mechanistic Analysis of Looped Reasoning Language Models
Looped LLMs converge to distinct cyclic fixed points per layer, repeating feedforward-style inference stages across recurrences.
-
Hyperloop Transformers
Hyperloop Transformers outperform standard and mHC Transformers with roughly 50% fewer parameters by looping a middle block of layers and applying hyper-connections only after each loop.