arXiv:2610.26030v2 Announce Type: replace Abstract: Looped transformers reuse a shared block of layers to increase computational depth without increasing the number of trainable parameters. They are...
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:2610.19768v1 Announce Type: new Abstract: Looped transformers compute by applying one block repeatedly, so they can run for more loops than they were trained with. Recurrent reasoners are known...
The paper demonstrates that neural networks can maintain perfect training accuracy while their training cross‑entropy remains nearly flat at a positive level, a phenomenon observed on modular addition tasks. Using ReLU networks with supported‑Polar hidden updates, normalized output‑layer updates, and weight decay, the authors show that hidden features evolve and held‑out accuracy can rise from zero to above 90% even as cross‑entropy stays flat. Theoretical results for one‑hidden‑layer networks and empirical evidence from deeper networks and transformers confirm that correct classification need not coincide with minimal cross‑entropy, challenging conventional assumptions about loss plateaus.
The paper introduces Stiefel Attention, which constrains the query and key projection matrices of transformers to the Stiefel manifold and optimizes them with a Riemannian Adam variant. It demonstrates that this approach yields steepest‑descent updates, is well‑conditioned, and preserves learned attention geometry during weight decay. Empirical results show significant accuracy gains on modular arithmetic grokking and CIFAR‑10 patches, with the improvement attributed to a step‑scale‑free update rule rather than equivariance or projector changes.
The paper argues that the policy governing how tensors are rounded and reused during the backward pass—termed the backward‑state policy—is an integral part of the learning algorithm, not merely a memory or precision detail. Experiments with 390 M‑parameter models show that whether the backward pass reuses a forward’s rounded output or generates a new rounding can decisively affect training success, even when copy accuracy is high. The authors propose a method to determine, for each operator, which value should be read or substituted to preserve the correct gradient, and validate these predictions on PyTorch and Transformer Engine.
arXiv:2608.23573v1 Announce Type: new Abstract: A trained transformer's weight magnitudes can be summarized by a two-parameter Weibull distribution whose shape $k \approx 1.2$ is stable across layers...
arXiv:2607. 20594v1 Announce Type: cross Abstract: When does a weight-tied looped transformer -- one block applied T times -- implement an actual algorithm?
arXiv:2607. 14427v1 Announce Type: new Abstract: A depth-recurrent transformer applies a weight-tied core a variable number of times, and prior work has shown that training with a randomized recursion count yields one checkpoint usable across a range of inference depths.
arXiv:2606. 07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently.
arXiv:2606. 18524v1 Announce Type: new Abstract: Looped (weight-tied) Transformers apply a shared residual block $N$ times ($h \leftarrow h + \varepsilon\,f(h)$, same $f$ at each step), increasing effective depth without adding parameters.
arXiv:2607. 09791v1 Announce Type: new Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.