No article text was recorded for this version.
quadratic attention complexity (computational scaling bottleneck)
Version 1 of 177 papers79 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Two Steps Forward and One Behind: Rethinking Time Series Forecasting with Deep Learning
- Blog: VQ-TR: Vector Quantized Attention for Time Series Forecasting
- Blog: BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis
- Blog: CAUSE: Learning Granger Causality from Event Sequences using Attribution Methods
- Blog: A comprehensive survey of deep learning for time series forecasting: architectural diversity and open challenges
- Blog: CASA: CNN Autoencoder-based Score Attention for Efficient Multivariate Long-term Time-series Forecasting
- Blog: Satellite Image Time-Series Classification with Inception-Enhanced Temporal Attention Encoder
- Blog: SMARTformer: Semi-Autoregressive Transformer with Efficient Integrated Window Attention for Long Time Series Forecasting
- Blog: Modeling and Monitoring Erosion of the Leading Edge of Wind Turbine Blades
- Blog: Triformer: Triangular, Variable-Specific Attentions for Long Sequence Multivariate Time Series Forecasting
- Blog: Towards Robust Deterministic and Probabilistic Modeling for Predictive Learning
- Blog: RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting
- Blog: Reverso: Efficient Time Series Foundation Models for Zero-shot Forecasting
- Blog: TimeStacker: A Novel Framework with Multilevel Observation for Capturing Nonstationary Patterns in Time Series Forecasting
- Blog: Affirm: Interactive Mamba with Adaptive Fourier Filters for Long-term Time Series Forecasting
- Blog: TSLANet: Rethinking Transformers for Time Series Representation Learning
- Blog: Decentralized Attention Fails Centralized Signals: Rethinking Transformers for Medical Time Series
- Blog: Spatio-temporal Attention Model for Tactile Texture Recognition
- Blog: PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling
- Blog: Leveraging Multiple Relations for Fashion Trend Forecasting Based on Social Media
- Blog: FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
- Blog: TimelyGPT: Recurrent Convolutional Transformer for Long Time-series Representation
- Blog: SpoT-Mamba: Learning Long-Range Dependency on Spatio-Temporal Graphs with Selective State Spaces
- Blog: Attention-based workload prediction and dynamic resource allocation for heterogeneous computing environments
- Blog: Scene Memory Transformer for Embodied Agents in Long-Horizon Tasks
- Blog: LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
- Blog: Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term Time Series Forecasting
- Blog: End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes
- Blog: PRformer: Pyramidal Recurrent Transformer for Multivariate Time Series Forecasting
- Blog: FIM: Frequency-Aware Multi-View Interest Modeling for Local-Life Service Recommendation
- Blog: Exploring Historical Information for RGBE Visual Tracking with Mamba
- Blog: Scaling Representation Learning from Ubiquitous ECG with State-Space Models
- Blog: Periodicity Decoupling Framework for Long-term Series Forecasting
- Blog: A Diffusion Model for Regular Time Series Generation from Irregular Data with Completion and Masking
- Blog: Dynamic Memory based Attention Network for Sequential Recommendation
- Blog: SpikF: Spiking Fourier Network for Efficient Long-term Prediction
- Blog: Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
- Blog: Rethinking Time-Series Imputation as Conditional Inference along Temporal Evolution
- Blog: Timelygpt: extrapolatable transformer pre-training for long-term time-series forecasting in healthcare
- Blog: NHITS: Neural Hierarchical Interpolation for Time Series Forecasting
- Blog: MedMamba: Multi-View State Space Models with Adaptive Graph Learning for Medical Time Series Classification
- Blog: Deep Structural Point Process for Learning Temporal Interaction Networks
- Blog: Linear Recurrent Units for Sequential Recommendation
- Blog: MambaMOS: LiDAR-based 3D Moving Object Segmentation with Motion-aware State Space Model
- Blog: A Survey on Deep Learning based Time Series Analysis with Frequency Transformation
- Blog: Efficient Noise-Decoupling for Multi-Behavior Sequential Recommendation
- Blog: Deep Continuous-Time State-Space Models for Marked Event Sequences
- Blog: SVP-T: A Shape-Level Variable-Position Transformer for Multivariate Time Series Classification
- Blog: Learning Soft Sparse Shapes for Efficient Time-Series Classification
- Blog: Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting
- Blog: TimeMRA: LLM-Empowered Time Series Forecasting via Multi-Scale Retrieval-Augmented Representations
- Blog: Causal Contrastive Learning for Counterfactual Regression Over Time
- Blog: BolT: Fused window transformers for fMRI time series analysis
- Blog: Meta-Black-Box-Optimization through Offline Q-function Learning
- Blog: Effective and Efficient Representation Learning for Flight Trajectories
- Blog: Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting
- Blog: MoFo: Empowering Long-term Time Series Forecasting with Periodic Pattern Modeling
- Blog: KT-LLM: an evidence-grounded and sequence text framework for auditable kidney transplant modeling
- Blog: EntroPE: Entropy-Guided Dynamic Patch Encoder for Time Series Forecasting
- Blog: FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting
Showing 60 of 77 papers.
History & citation
Current · Permanent link
Cite this direction
Latest version (a living page):
@misc{lacuna_quadratic_attention_complexity_computati_1caa640b,
title = {quadratic attention complexity (computational scaling bottleneck)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/quadratic-attention-complexity-computational-scaling-bottleneck/rdr_1caa640beeca4f10a0e15f038d88288a},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-19},
}This exact version (version 1, frozen text):
@misc{lacuna_quadratic_attention_complexity_computati_1caa640b_v1,
title = {quadratic attention complexity (computational scaling bottleneck)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/quadratic-attention-complexity-computational-scaling-bottleneck/rdr_1caa640beeca4f10a0e15f038d88288a/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-19},
}