Imagen de Portada

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Beck, Maximilian, Schweighofer, Kajetan, Böck, Sebastian, Lehner, Sebastian, Hochreiter, Sepp
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
por: Beck, Maximilian, et al.
Publicado: (2025)

Vision-LSTM: xLSTM as Generic Vision Backbone
por: Alkin, Benedikt, et al.
Publicado: (2024)

Effective Distillation to Hybrid xLSTM Architectures
por: Hauzenberger, Lukas, et al.
Publicado: (2026)

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
por: Beck, Maximilian, et al.
Publicado: (2025)

Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
por: Aichberger, Lukas, et al.
Publicado: (2024)

xLSTM: Extended Long Short-Term Memory
por: Beck, Maximilian, et al.
Publicado: (2024)

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
por: Ielanskyi, Mykyta, et al.
Publicado: (2025)

On Information-Theoretic Measures of Predictive Uncertainty
por: Schweighofer, Kajetan, et al.
Publicado: (2024)

Improving Uncertainty Estimation through Semantically Diverse Language Generation
por: Aichberger, Lukas, et al.
Publicado: (2024)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
por: Schmied, Thomas, et al.
Publicado: (2024)

The Disparate Benefits of Deep Ensembles
por: Schweighofer, Kajetan, et al.
Publicado: (2024)

A Diffusion Model Framework for Unsupervised Neural Combinatorial Optimization
por: Sanokowski, Sebastian, et al.
Publicado: (2024)

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences
por: Schmidinger, Niklas, et al.
Publicado: (2024)

Rethinking Losses for Diffusion Bridge Samplers
por: Sanokowski, Sebastian, et al.
Publicado: (2025)

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

xLSTM-ECG: Multi-label ECG Classification via Feature Fusion with xLSTM
por: Kang, Lei, et al.
Publicado: (2025)

xLSTMTime : Long-term Time Series Forecasting With xLSTM
por: Alharthi, Musleh, et al.
Publicado: (2024)

pLSTM: parallelizable Linear Source Transition Mark networks
por: Pöppel, Korbinian, et al.
Publicado: (2025)

Benchmarking Transformer and xLSTM for Time-Series Forecasting of Heat Consumption
por: Wahl, Marja, et al.
Publicado: (2026)

Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification
por: Auer, Andreas, et al.
Publicado: (2025)

Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
por: Zhu, Qinfeng, et al.
Publicado: (2024)

MolGraph-xLSTM: A graph-based dual-level xLSTM framework with multi-head mixture-of-experts for enhanced molecular representation and interpretability
por: Sun, Yan, et al.
Publicado: (2025)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
por: Auer, Andreas, et al.
Publicado: (2025)

Scalable Discrete Diffusion Samplers: Combinatorial Optimization and Statistical Physics
por: Sanokowski, Sebastian, et al.
Publicado: (2025)

xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
por: Faber, Kamil, et al.
Publicado: (2025)

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
por: Kraus, Maurice, et al.
Publicado: (2024)

xLSTM-PINN: Memory-Gated Spectral Remodeling for Physics-Informed Learning
por: Tao, Ze, et al.
Publicado: (2025)

Overcoming Saturation in Density Ratio Estimation by Iterated Regularization
por: Gruber, Lukas, et al.
Publicado: (2024)

Enhancing Spatiotemporal Networks with xLSTM: A Scalar LSTM Approach for Cellular Traffic Forecasting
por: Ali, Khalid, et al.
Publicado: (2025)

Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures
por: Thiombiano, Abdoul Majid O., et al.
Publicado: (2025)

Energy-based Hopfield Boosting for Out-of-Distribution Detection
por: Hofmann, Claus, et al.
Publicado: (2024)

AP-OOD: Attention Pooling for Out-of-Distribution Detection
por: Hofmann, Claus, et al.
Publicado: (2026)

MoxE: Mixture of xLSTM Experts with Entropy-Aware Routing for Efficient Language Modeling
por: Thiombiano, Abdoul Majid O., et al.
Publicado: (2025)

Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned
por: Schweighofer, Kajetan, et al.
Publicado: (2025)

Uncertainty Quantification for Regression using Proper Scoring Rules
por: Fishkov, Alexander, et al.
Publicado: (2025)

Linear Alignment of Vision-language Models for Image Captioning
por: Paischer, Fabian, et al.
Publicado: (2023)

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies
por: Schweighofer, Kajetan, et al.
Publicado: (2026)

A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM Networks
por: Sarlakifar, Faezeh, et al.
Publicado: (2025)

xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
por: Kühne, Nikolai Lund, et al.
Publicado: (2025)

Efficient Pre-Training of LLMs through Truncated SVD Layers
por: Kamali, Kaivan, et al.
Publicado: (2026)