arXiv Machine Learning
Jun 5
Pretraining Recurrent Networks without Recurrence
arXiv:2606. 06479v1 Announce Type: new Abstract: Training recurrent neural networks (RNNs) requires assigning credit across long sequences of computations.
Maglev: Sliding Recurrent Memory
arXiv:2608. 02870v1 Announce Type: new Abstract: We introduce \ours{}, a recurrent Transformer architecture with fixed-size memory that generalizes sliding-window attention while remaining parallelizable during training.
Related stories
arXiv Machine Learning
Sep 24
Attention Routing Stabilizes Early: Working-Set Inference for Recurrent Language Models
The paper investigates how attention dynamics evolve across recurrent depth in language models, finding that attention support stabilizes early while hidden states and outputs take longer. It proposes WISE, a training‑free method that uses full attention in early steps and then reuses the discovered sparse working set for later steps, preserving performance on multi‑hop QA tasks. Experiments show that WISE maintains quality up to 2K context, offers measurable speedups, and highlights the importance of recurrent discovery of attention support.
arXiv Machine Learning
Sep 2
Latent Recurrent Transformer: Architecture Exploration, Training Strategies, and Scaling Behavior
arXiv:2605.26797v2 Announce Type: replace Abstract: We study Latent Recurrent Transformer (LRT), a lightweight augmentation of autoregressive transformers that reuses a high-level source-layer hidden...
arXiv AI
Jul 29
Raven: High-Recall Sequence Modeling with Sparse Memory Routing
arXiv:2607. 25357v1 Announce Type: cross Abstract: Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory.
arXiv Machine Learning
Jul 14
Controllably Efficient Language Models
arXiv:2511. 05313v2 Announce Type: replace Abstract: The substantial inference costs of attention in transformers motivated the development of efficient sequence mixers: namely sparse and sliding window attention, convolutions and linear attention.
arXiv Machine Learning
Aug 31
Sliding-window beats linear attention
arXiv:2608.28444v1 Announce Type: cross Abstract: Due to the nature of quadratic attention, Large Language Models (LLMs) consume a lot of memory and energy. Every new token costs more than the previo...
arXiv Computation and Language
Sep 16
Persistent Recurrent Memory Between Transformer Layers - Improves Language Model Generalization
The paper proposes a lightweight recurrent memory module inserted between the lower and upper halves of a 6‑layer decoder‑only transformer. This module, which uses cross‑attention to observe hidden states, a GRU to update a persistent state, and gated addition to modulate subsequent layers, adds only 3.7% more parameters. It reduces evaluation loss by 28.5% and narrows the generalization gap, with ablations showing the benefit comes solely from the memory topology rather than auxiliary losses.
arXiv Machine Learning
Jun 11
On Subquadratic Architectures: From Applications to Principles
arXiv:2606. 12364v1 Announce Type: new Abstract: Transformers dominate modern sequence modeling, but their quadratic attention incurs substantial computational cost.
arXiv AI
Jun 24
WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech Models
arXiv:2604. 08558v2 Announce Type: replace-cross Abstract: Recent decoder-only autoregressive text-to-speech (AR-TTS) models produce high-fidelity speech, but their memory and compute costs scale quadratically with sequence length due to full self-attention.
arXiv Machine Learning
Jun 16
Next-Latent Prediction Transformers Learn Compact World Models
arXiv:2511. 05963v4 Announce Type: replace Abstract: Transformers replace recurrence with a memory that grows with sequence length and self-attention that enables ad-hoc lookups over past tokens.
arXiv AI
Jun 4
MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
arXiv:2506. 05233v2 Announce Type: replace-cross Abstract: Sequence modeling is currently dominated by causal transformer architectures that use softmax self-attention.
arXiv Machine Learning
Jun 17
Olmo Hybrid: From Theory to Practice and Back
arXiv:2604. 03444v4 Announce Type: replace Abstract: Recent work has demonstrated the potential of non-transformer language models, especially linear recurrent neural networks (RNNs) and hybrid models that mix recurrence and attention.