recurrent-models

Tag

Cards List
#recurrent-models

Recurrent Looped Transformer

Hacker News Top · 2026-09-13 Cached

Recurrent Looped Transformer (RLT) is a novel architecture combining a causal encoder with a recurrent decoder to achieve latent reasoning with unbounded temporal depth, model-hardware co-design, and model-RL algorithm co-design.

0 favorites 0 likes
#recurrent-models

Fast Weight Attention for Continual Learning

Hugging Face Daily Papers · 2026-08-27 Cached

This paper analyzes recurrent fast-weight memories and selective state-space models as online learning rules, deriving normalized update families that improve length extrapolation and remain competitive in language modeling.

0 favorites 0 likes
#recurrent-models

Steering Recurrent Reasoners at Inference Time with Readout Feedback

arXiv cs.LG · 2026-08-26 Cached

The paper introduces Readout Feedback (RoFB), a test-time intervention that steers latent dynamics in recurrent reasoning models using their own readout probabilities, achieving performance gains on Sudoku and Maze tasks without retraining.

0 favorites 0 likes
#recurrent-models

Parameter-Efficient Quantum-Inspired Fast Weight Programmers for Traffic-Matrix Forecasting

Hugging Face Daily Papers · 2026-06-26 Cached

This paper proposes quantum-inspired recurrent models (QKAN-FWPs) for traffic-matrix forecasting, demonstrating superior accuracy with fewer parameters compared to LSTM baselines.

0 favorites 0 likes
#recurrent-models

Frequency Domain Reservoir Computing

arXiv cs.LG · 2026-06-25 Cached

This paper introduces FRESCO, an Echo State Network architecture operating entirely in the frequency domain to achieve O(N) complexity for dense recurrent updates, matching state-of-the-art performance on benchmarks while reducing computational costs.

0 favorites 0 likes
#recurrent-models

Mechanical Field Networks: Structured Neural Dynamics for Multivariate Systems

arXiv cs.LG · 2026-06-11 Cached

This paper introduces MF-Net, a recurrent dynamical model that represents multivariate systems through a shared field state and learns a mechanical transition for joint evolution. It achieves competitive forecasting while enabling interpretable structural readout of learned relations.

0 favorites 0 likes
#recurrent-models

Generic Triple-Latent Compression with Gated Associative Retrieval

arXiv cs.CL · 2026-06-05 Cached

This paper introduces generic triple-latent recurrent models that compress token pair interactions into a latent state, and a gated associative retrieval variant that improves exact recall. The hybrid model outperforms Transformers on byte-level WikiText-2 and a tokenized language benchmark, achieving up to 41.9% associative recall versus 25%.

0 favorites 0 likes
#recurrent-models

WriteSAE: Sparse Autoencoders for Recurrent State

Hugging Face Daily Papers · 2026-05-12 Cached

WriteSAE introduces the first sparse autoencoder that decomposes matrix cache writes in state-space and hybrid recurrent language models, enabling superior token-level interventions compared to existing methods.

0 favorites 0 likes
#recurrent-models

Rethinking State Tracking in Recurrent Models Through Error Control Dynamics

Hugging Face Daily Papers · 2026-05-08 Cached

This paper argues that robust state tracking in recurrent models depends on error control dynamics rather than just expressive capacity, proving that affine recurrent networks suffer from accumulating errors that limit their effective horizon.

0 favorites 0 likes
← Back to home

Submit Feedback