Image de couverture de livre

Effective Distillation to Hybrid xLSTM Architectures

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Hauzenberger, Lukas, Schmidinger, Niklas, Schmied, Thomas, Hartl, Anamaria-Roberta, Stap, David, Hoedt, Pieter-Jan, Beck, Maximilian, Böck, Sebastian, Klambauer, Günter, Hochreiter, Sepp
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences
par: Schmidinger, Niklas, et autres
Publié: (2024)

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference
par: Beck, Maximilian, et autres
Publié: (2025)

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks
par: Schmied, Thomas, et autres
Publié: (2024)

xLSTM: Extended Long Short-Term Memory
par: Beck, Maximilian, et autres
Publié: (2024)

xLSTM Scaling Laws: Competitive Performance with Linear Time-Complexity
par: Beck, Maximilian, et autres
Publié: (2025)

Vision-LSTM: xLSTM as Generic Vision Backbone
par: Alkin, Benedikt, et autres
Publié: (2024)

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels
par: Beck, Maximilian, et autres
Publié: (2025)

Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used
par: Shakya, Srijan, et autres
Publié: (2026)

Parameter Efficient Fine-tuning via Explained Variance Adaptation
par: Paischer, Fabian, et autres
Publié: (2024)

TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learning
par: Auer, Andreas, et autres
Publié: (2025)

pLSTM: parallelizable Linear Source Transition Mark networks
par: Pöppel, Korbinian, et autres
Publié: (2025)

xLSTM-SENet: xLSTM for Single-Channel Speech Enhancement
par: Kühne, Nikolai Lund, et autres
Publié: (2025)

xLSTM-ECG: Multi-label ECG Classification via Feature Fusion with xLSTM
par: Kang, Lei, et autres
Publié: (2025)

FlashRNN: I/O-Aware Optimization of Traditional RNNs on modern hardware
par: Pöppel, Korbinian, et autres
Publié: (2024)

VN-EGNN: E(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
par: Sestak, Florian, et autres
Publié: (2024)

Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures
par: Thiombiano, Abdoul Majid O., et autres
Publié: (2025)

When Mamba Meets xLSTM: An Efficient and Precise Method with the xLSTM-VMUNet Model for Skin lesion Segmentation
par: Fang, Zhuoyi, et autres
Publié: (2024)

Unlocking the Working Memory of Large Language Models for Latent Reasoning
par: Aichberger, Lukas, et autres
Publié: (2026)

xLSTMTime : Long-term Time Series Forecasting With xLSTM
par: Alharthi, Musleh, et autres
Publié: (2024)

Seg-LSTM: Performance of xLSTM for Semantic Segmentation of Remotely Sensed Images
par: Zhu, Qinfeng, et autres
Publié: (2024)

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

xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
par: Faber, Kamil, et autres
Publié: (2025)

Benchmarking Transformer and xLSTM for Time-Series Forecasting of Heat Consumption
par: Wahl, Marja, et autres
Publié: (2026)

Enhancing Spatiotemporal Networks with xLSTM: A Scalar LSTM Approach for Cellular Traffic Forecasting
par: Ali, Khalid, et autres
Publié: (2025)

Pre-trained Forecasting Models: Strong Zero-Shot Feature Extractors for Time Series Classification
par: Auer, Andreas, et autres
Publié: (2025)

Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measure
par: Aichberger, Lukas, et autres
Publié: (2024)

xLSTM-PINN: Memory-Gated Spectral Remodeling for Physics-Informed Learning
par: Tao, Ze, et autres
Publié: (2025)

Retrieval-Augmented Decision Transformer: External Memory for In-context RL
par: Schmied, Thomas, et autres
Publié: (2024)

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories
par: Kraus, Maurice, et autres
Publié: (2024)

MAL: Cluster-Masked and Multi-Task Pretraining for Enhanced xLSTM Vision Performance
par: Huang, Wenjun, et autres
Publié: (2024)

AF-MAT: Aspect-aware Flip-and-Fuse xLSTM for Aspect-based Sentiment Analysis
par: Lawan, Adamu, et autres
Publié: (2025)

Are Vision xLSTM Embedded UNet More Reliable in Medical 3D Image Segmentation?
par: Dutta, Pallabi, et autres
Publié: (2024)

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

A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM Networks
par: Sarlakifar, Faezeh, et autres
Publié: (2025)

On Information-Theoretic Measures of Predictive Uncertainty
par: Schweighofer, Kajetan, et autres
Publié: (2024)

MIM-Refiner: A Contrastive Learning Boost from Intermediate Pre-Trained Representations
par: Alkin, Benedikt, et autres
Publié: (2024)

Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generation
par: Ielanskyi, Mykyta, et autres
Publié: (2025)

Improving Uncertainty Estimation through Semantically Diverse Language Generation
par: Aichberger, Lukas, et autres
Publié: (2024)

xLSTM-UNet can be an Effective 2D & 3D Medical Image Segmentation Backbone with Vision-LSTM (ViL) better than its Mamba Counterpart
par: Chen, Tianrun, et autres
Publié: (2024)

xLSTM-FER: Enhancing Student Expression Recognition with Extended Vision Long Short-Term Memory Network
par: Huang, Qionghao, et autres
Publié: (2024)