paper-with-me

홈 › Papers

A Large Recurrent Action Model: xLSTM enables Fast Inference for Robotics Tasks

2024-10-29 · Thomas Schmied, Thomas Adler, Vihang Patil, Maximilian Beck, Korbinian Pöppel, Johannes Brandstetter, Günter Klambauer, Razvan Pascanu, Sepp Hochreiter

In recent years, there has been a trend in the field of Reinforcement Learning (RL) towards large action models trained offline on large-scale datasets via sequence modeling. Existing models are primarily based on the Transformer architecture, which result in powerful agents. However, due to slow inference times, Transformer-based approaches are impractical for real-time applications, such as robotics. Recently, modern recurrent architectures, such as xLSTM and Mamba, have been proposed that exhibit parallelization benefits during training similar to the Transformer architecture while offering fast inference. In this work, we study the aptitude of these modern recurrent architectures for large action models. Consequently, we propose a Large Recurrent Action Model (LRAM) with an xLSTM at its core that comes with linear-time inference complexity and natural sequence length extrapolation abilities. Experiments on 432 tasks from 6 domains show that LRAM compares favorably to Transformers in terms of performance and speed.

📄 PDF Abstract BibTeX arXiv:2410.22391

Code (1)

ml-jku/lram 공식 구현 pytorch

Tasks

MambaReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Attention 설명 없음

Similar Papers 제목 키워드 기반

xLSTM 7B: A Recurrent LLM for Fast and Efficient Inference

2025-03-17 · Maximilian Beck, Korbinian Pöppel, Phillip Lippe, Richard Kurle 외

Recent breakthroughs in solving reasoning, math and coding problems with Large Language Models (LLMs) have been enabled by investing substantial computation budgets at inference time. Therefore, inference speed is one of…

MambaMath

Distil-xLSTM: Learning Attention Mechanisms through Recurrent Structures

2025-03-24 · Abdoul Majid O. Thiombiano, Brahim Hnich, Ali Ben Mrad, Mohamed Wiem Mkaouer

The current era of Natural Language Processing (NLP) is dominated by Transformer models. However, novel architectures relying on recurrent mechanisms, such as xLSTM and Mamba, have been proposed as alternatives to attent…

Language ModelingLanguage ModellingLarge Language ModelMamba+1

Linear-Time and Constant-Memory Text Embeddings Based on Recurrent Language Models

2026-04-20 · Tobias Grantner, Emanuel Sallinger, Martin Flechl arxiv

Transformer-based embedding models suffer from quadratic computational and linear memory complexity, limiting their utility for long sequences. We propose recurrent architectures as an efficient alternative, introducing …

StoxLSTM: A Stochastic Extended Long Short-Term Memory Network for Time Series Forecasting

2025-09-01 · Zihao Wang, Yunjie Li, Lingmin Zan, Zheng Gong 외 arxiv

The Extended Long Short-Term Memory (xLSTM) network has demonstrated strong capability in modeling complex long-term dependencies in time series data. Despite its success, the deterministic architecture of xLSTM limits i…

Time Series Forecasting

Bio-xLSTM: Generative modeling, representation and in-context learning of biological and chemical sequences

2024-11-06 · Niklas Schmidinger, Lisa Schneckenreiter, Philipp Seidl, Johannes Schimunek 외

Language models for biological and chemical sequences enable crucial applications such as drug discovery, protein engineering, and precision medicine. Currently, these language models are predominantly based on Transform…

Drug DiscoveryIn-Context Learning