On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,657 papers · 148 categories

Trend · papers per month

count % of corpus

7 results for “xLSTM”

A Deep Reinforcement Learning Approach to Automated Stock Trading, using xLSTM Networkscs.CE

Study uses xLSTM in DRL for better stock trading performance.

problem Limited performance of LSTM in dynamic stock trading environments.

method Combines xLSTM in actor and critic components with PPO optimization.

result xLSTM-based model outperforms LSTM in trading metrics.

Deep Reinforcement Learning Stock Trading xLSTM Proximal Policy Optimization Financial Markets

2025-03-12abs ↗pdf ↗

xLSTM: Extended Long Short-Term Memorycs.LG

Extended LSTM improves language modeling performance.

problem Improving LSTM for large-scale language modeling.

method Exponential gating, modified memory structure, and residual stacking.

result xLSTM outperforms state-of-the-art models in performance and scaling.

LSTM Transformer Language Modeling Exponential Gating Memory Structure

2024-05-07abs ↗pdf ↗

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacitycs.LG

gLSTM improves graph neural networks by increasing storage capacity to prevent over-squashing.

problem Over-squashing in GNNs collapses information from a large receptive field into a single vector, creating an information bottleneck.

method Introduced a new synthetic task to measure over-squashing and adapted ideas from sequence modeling to develop gLSTM, a novel GNN architecture with improved capacity.

result gLSTM architecture demonstrates strong performance on synthetic and real-world graph benchmarks, mitigating over-squashing.

Graph Neural Networks Over-Squashing Capacity Receptive Field Associative Memories

2025-10-09abs ↗pdf ↗

Deep Learning for Financial Time Series: A Large-Scale Benchmark of Risk-Adjusted Performanceq-fin.TR

Benchmarking deep learning models for financial time series, focusing on risk-adjusted performance.

problem Optimizing risk-adjusted performance in financial time series prediction.

method Evaluation of various deep learning architectures including linear models, RNNs, transformers, state space models, and sequence representation approaches.

result Hybrid models like VSN with LSTM and xLSTM achieve the highest overall Sharpe ratio and superior downside adjusted characteristics.

deep learning financial time series risk-adjusted performance Sharpe ratio downside risk

2026-03-02abs ↗pdf ↗

CogScale: Scalable Benchmark for Sequence Processingcs.AI

CogScale benchmarks AI architectures for sequential processing.

problem Evaluating AI architectures' ability to process sequential information efficiently.

method 14 scalable synthetic tasks designed to isolate cognitive and memory abilities at different scales.

result Attention mechanisms and modern state-space models consistently maintain high performance as task difficulty scales.

AI benchmarks sequence processing cognitive abilities attention mechanisms state-space models

2026-05-19abs ↗pdf ↗

A Review of the Long Horizon Forecasting Problem in Time Series Analysiscs.LG

This review tackles long horizon forecasting in time series analysis using deep learning.

problem Long horizon forecasting in time series analysis.

method Incorporates deep learning techniques such as trend, seasonality, Fourier and wavelet transforms, and various model architectures.

result LHF is an error propagation problem, with models like xLSTM and Triformer showing better performance.

long horizon forecasting time series analysis deep learning error propagation multi-layer perceptron

2025-06-15abs ↗pdf ↗

pLSTM: parallelizable Linear Source Transition Mark networkscs.LG

pLSTM tackles long-range language modeling and computer vision tasks with parallelizable linear source transition mark networks.

problem Challenges of existing recurrent architectures in handling sequences and multi-dimensional data.

method Introduces pLSTM, a parallelizable linear source transition mark network for linear graphs and DAGs, addressing vanishing/exploding activation/gradient issues.

result pLSTM outperforms Transformers in long-range tasks like arrow-pointing extrapolation and image size extrapolation.

pLSTM parallelizable linear source transition Mark networks vanishing/exploding gradient

2025-06-13abs ↗pdf ↗