No article text was recorded for this version.
sequential processing bottleneck (sequential computation bottleneck)
Version 1 of 11,409 papers1,546 conceptsfrozen 2026-10-04
Papers in this version
- Blog: Multi-Head Highly Parallelized LSTM Decoder for Neural Machine Translation
- Blog: Autoregressive + Chain of Thought = Recurrent: Recurrence's Role in Language Models' Computability and a Revisit of Recurrent Transformer
- Blog: Bottleneck Analysis of Dynamic Graph Neural Network Inference on CPU and GPU
- Blog: Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks
- Blog: Single stream parallelization of generalized LSTM-like RNNs on a GPU
- Blog: Temporal Deformable Convolutional Encoder-Decoder Networks for Video Captioning.
- Blog: UFANS: U-shaped Fully-Parallel Acoustic Neural Structure For Statistical Parametric Speech Synthesis With 20X Faster
- Blog: Recurrent Neural Network from Adder's Perspective: Carry-lookahead RNN
- Blog: Single Stream Parallelization of Recurrent Neural Networks for Low Power and Fast Inference
- Blog: Training RNNs as Fast as CNNs
- Blog: GRN: Gated Relation Network to Enhance Convolutional Neural Network for Named Entity Recognition
- Blog: Quasi-Recurrent Neural Networks
- Blog: Dependency Parsing with Dilated Iterated Graph CNNs
- Blog: Diagonal Batching Unlocks Parallelism in Recurrent Memory Transformers for Long Contexts
- Blog: A Convolutional Encoder Model for Neural Machine Translation
- Blog: Language Models Need Inductive Biases to Count Inductively
- Blog: Accelerating Recurrent Neural Networks for Gravitational Wave Experiments
- Blog: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
- Blog: Mini-Batch Learning Strategies for modeling long term temporal dependencies: A study in environmental applications
- Blog: Towards Better Modeling Hierarchical Structure for Self-Attention with Ordered Neurons
- Blog: Efficient Image Compression Using Advanced State Space Models
- Blog: A Decomposable Attention Model for Natural Language Inference
- Blog: Sliced Recurrent Neural Networks
- Blog: Gated Convolutional Neural Network for Sentence Matching
- Blog: Gaussian Process Regression in Logarithmic Time
- Blog: Sequence-to-Sequence Speech Recognition with Time-Depth Separable Convolutions
- Blog: R2D2: Recursive Transformer based on Differentiable Tree for Interpretable Hierarchical Language Modeling
- Blog: Constructing Long Short-Term Memory based Deep Recurrent Neural Networks for Large Vocabulary Speech Recognition
- Blog: Echo State Transformer: When chaos brings memory
- Blog: The Parallel Expert Parser (PEP): A Thoroughly Revised Descendant of the Word Expert Parser (WEP)
- Blog: Joint Distance Maps Based Action Recognition With Convolutional Neural Networks
- Blog: FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement
- Blog: GRAFX: An Open-Source Library for Audio Processing Graphs in PyTorch
- Blog: RecNets: Channel-wise Recurrent Convolutional Neural Networks
- Blog: DPCRN: Dual-Path Convolution Recurrent Network for Single Channel Speech Enhancement
- Blog: To Cache or Not To Cache? Experiments with Adaptive Models in Statistical Machine Translation
- Blog: Learning Generic Sentence Representations Using Convolutional Neural Networks
- Blog: Accelerating Model-Based Reinforcement Learning with State-Space World Models
- Blog: Non-local Recurrent Regularization Networks for Multi-view Stereo
- Blog: Simple Recurrence Improves Masked Language Models
- Blog: DiSAN: Directional Self-Attention Network for RNN/CNN-free Language Understanding
- Blog: Parallelization of Non-linear State-Space Models: Scaling Up Liquid-Resistance Liquid-Capacitance Networks for Efficient Sequence Modeling
- Blog: Dilated Recurrent Neural Networks
- Blog: Speed up of recurrent neural network language models with sentence independent subsampling stochastic gradient descent
- Blog: Convolutional Sequence to Sequence Learning
- Blog: Quasi-Recurrent Neural Networks
- Blog: A Study of All-Convolutional Encoders for Connectionist Temporal Classification
- Blog: Sequencer: Deep LSTM for Image Classification
- Blog: Parallelizing Linear Transformers with the Delta Rule over Sequence Length
- Blog: Recurrence Boosts Diversity! Revisiting Recurrent Latent Variable in Transformer-Based Variational AutoEncoder for Diverse Text Generation
- Blog: Bisimulation Metric for Model Predictive Control
- Blog: Real-time speech modeling using computationally efficient locally recurrent neural networks (CERNs)
- Blog: Fixed-Point RNNs: Interpolating from Diagonal to Dense
- Blog: Fast and Accurate Entity Recognition with Iterated Dilated Convolutions
- Blog: Parallel Training of GRU Networks with a Multi-Grid Solver for Long Sequences
- Blog: Minimal Convolutional RNNs Accelerate Spatiotemporal Learning
- Blog: OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
- Blog: Simplifying Neural Machine Translation with Addition-Subtraction Twin-Gated Recurrent Networks
- Blog: Memory-Efficient Looped Transformer: Decoupling Compute from Memory in Looped Language Models
- Blog: Why Are Linear RNNs More Parallelizable?
Showing 60 of 1,409 papers.
History & citation
Current · Permanent link
- Scaling Recurrent Networks with Exponential Gating and Matrix Memory merged into this direction (58% overlap)
- Parallelizable Recurrence for Efficient Sequence Modeling merged into this direction (73% overlap)
- Parallel Recurrence through Decoupled Linear Transformations merged into this direction (67% overlap)
- Parallel Sequence Modeling without Recurrence merged into this direction (96% overlap)
- Parallel Sequence Modeling through Non Recurrent Attention merged into this direction (73% overlap)
- Replacing Recurrence with Parallel Sequence Modeling merged into this direction (51% overlap)
- Efficient Sequence Modeling via Linear State Space Duality merged into this direction (50% overlap)
Cite this direction
Latest version (a living page):
@misc{lacuna_sequential_processing_bottleneck_sequent_eea2e71c,
title = {sequential processing bottleneck (sequential computation bottleneck)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sequential-processing-bottleneck-sequential-computation-bottleneck/rdr_eea2e71c66d04e26baea5cca79ddde56},
note = {Latest version of a living research direction; cite a version for a fixed text. Accessed 2026-11-20},
}This exact version (version 1, frozen text):
@misc{lacuna_sequential_processing_bottleneck_sequent_eea2e71c_v1,
title = {sequential processing bottleneck (sequential computation bottleneck)},
author = {{Lacuna}},
howpublished = {Lacuna research direction},
year = {2026},
url = {https://lacuna.tiptreesystems.com/direction/sequential-processing-bottleneck-sequential-computation-bottleneck/rdr_eea2e71c66d04e26baea5cca79ddde56/v/1},
note = {Version 1, frozen 2026-10-04. Accessed 2026-11-20},
}