Imagen de Portada

Implicit Language Models are RNNs: Balancing Parallelization and Expressivity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Schöne, Mark, Rahmani, Babak, Kremer, Heiner, Falck, Fabian, Ballani, Hitesh, Gladrow, Jannes
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Learning State-Tracking from Code Using Linear RNNs
por: Siems, Julien, et al.
Publicado: (2026)

Learning to (Learn at Test Time): RNNs with Expressive Hidden States
por: Sun, Yu, et al.
Publicado: (2024)

Balancing Sparse RNNs with Hyperparameterization Benefiting Meta-Learning
por: Hershey, Quincy, et al.
Publicado: (2025)

Debugging code world models
por: Rahmani, Babak
Publicado: (2026)

M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling
por: Mishra, Mayank, et al.
Publicado: (2026)

Memory Caching: RNNs with Growing Memory
por: Behrouz, Ali, et al.
Publicado: (2026)

Were RNNs All We Needed?
por: Feng, Leo, et al.
Publicado: (2024)

Expressive Power of Implicit Models: Rich Equilibria and Test-Time Scaling
por: Liu, Jialin, et al.
Publicado: (2025)

$\texttt{lrnnx}$: A library for Linear RNNs
por: Bania, Karan, et al.
Publicado: (2026)

Pessimistic Iterative Planning with RNNs for Robust POMDPs
por: Galesloot, Maris F. L., et al.
Publicado: (2024)

HadamRNN: Binary and Sparse Ternary Orthogonal RNNs
por: Foucault, Armand, et al.
Publicado: (2025)

Does Transformer Interpretability Transfer to RNNs?
por: Paulo, Gonçalo, et al.
Publicado: (2024)

Paradoxical noise preference in RNNs
por: Eckstein, Noah, et al.
Publicado: (2026)

The Expressivity Boundary of Probabilistic Circuits: A Comparison with Large Language Models
por: Zhao, Zhiyu, et al.
Publicado: (2026)

Message Passing on the Edge: Towards Scalable and Expressive GNNs
por: Barceló, Pablo, et al.
Publicado: (2025)

Verification of the Implicit World Model in a Generative Model via Adversarial Sequences
por: Balogh, András, et al.
Publicado: (2026)

Learning Dynamics of RNNs in Closed-Loop Environments
por: Ger, Yoav, et al.
Publicado: (2025)

Compositional Reasoning with Transformers, RNNs, and Chain of Thought
por: Yehudai, Gilad, et al.
Publicado: (2025)

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
por: Pöppel, Korbinian, et al.
Publicado: (2024)

Weight Sparsity Complements Activity Sparsity in Neuromorphic Language Models
por: Mukherji, Rishav, et al.
Publicado: (2024)

Renaissance of RNNs in Streaming Clinical Time Series: Compact Recurrence Remains Competitive with Transformers
por: Tong, Ran, et al.
Publicado: (2025)

Detecting Invariant Manifolds in ReLU-Based RNNs
por: Eisenmann, Lukas, et al.
Publicado: (2025)

Learning reveals invisible structure in low-rank RNNs
por: Ger, Yoav, et al.
Publicado: (2026)

How Expressive are Knowledge Graph Foundation Models?
por: Huang, Xingyue, et al.
Publicado: (2025)

Are Expressive Models Truly Necessary for Offline RL?
por: Wang, Guan, et al.
Publicado: (2024)

Expanding Expressivity in Transformer Models with MöbiusAttention
por: Halacheva, Anna-Maria, et al.
Publicado: (2024)

Least-Loaded Expert Parallelism: Load Balancing An Imbalanced Mixture-of-Experts
por: Nguyen, Xuan-Phi, et al.
Publicado: (2026)

TempoPFN: Synthetic Pre-training of Linear RNNs for Zero-shot Time Series Forecasting
por: Moroshan, Vladyslav, et al.
Publicado: (2025)

Bypassing the Rationale: Causal Auditing of Implicit Reasoning in Language Models
por: Sathyanarayanan, Anish, et al.
Publicado: (2026)

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
por: Wollschläger, Tom, et al.
Publicado: (2025)

On the Role of Depth in the Expressivity of RNNs
por: Lizaire, Maude, et al.
Publicado: (2026)

Remove Symmetries to Control Model Expressivity and Improve Optimization
por: Ziyin, Liu, et al.
Publicado: (2024)

Model Parallelism With Subnetwork Data Parallelism
por: Singh, Vaibhav, et al.
Publicado: (2025)

Reevaluation of Inductive Link Prediction
por: Ott, Simon, et al.
Publicado: (2024)

Taipan: Efficient and Expressive State Space Language Models with Selective Attention
por: Van Nguyen, Chien, et al.
Publicado: (2024)

On the Expressiveness and Length Generalization of Selective State-Space Models on Regular Languages
por: Terzić, Aleksandar, et al.
Publicado: (2024)

CombAlign: Enhancing Model Expressiveness in Unsupervised Graph Alignment
por: Chen, Songyang, et al.
Publicado: (2024)

Building Expressive and Tractable Probabilistic Generative Models: A Review
por: Sidheekh, Sahil, et al.
Publicado: (2024)

Curvature-Weighted Capacity Allocation: A Minimum Description Length Framework for Layer-Adaptive Large Language Model Optimization
por: Amaefuna, Theophilus, et al.
Publicado: (2026)

Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises
por: Rahmani, Abdellah, et al.
Publicado: (2025)