Research
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.

169,341 papers · 148 categories

Trend · papers per month

4896144192 · Jun 202019922001200920182026
48 results for sequence autoencoders

Deep neural networks can store and recall data efficiently.

problem Identifying computational mechanisms for memorization and retrieval of data.
method Training overparameterized autoencoders and sequence encoders using standard optimization methods.
result Overparameterized autoencoders and sequence encoders store and recall data efficiently as attractors.

LaMBO optimizes biological sequences using autoencoders and Bayesian optimization.

problem Bayesian optimization for drug design is limited by discrete, high-dimensional decision variables.
method Jointly trains denoising autoencoder with a Gaussian process head for gradient-based optimization in latent space.
result LaMBO outperforms genetic optimizers and requires no large pretraining corpus.

Novel fusion of autoencoders predicts sleepiness from speech.

problem Predicting sleepiness from speech recordings.
method Attention-based and recurrent sequence to sequence autoencoders for unsupervised representation learning.
result Fusion of autoencoders' representations achieves higher correlation with sleepiness scales.

TREP learns pedestrian trajectories efficiently without needing full datasets.

problem Learning fixed-length vector representations of variable-length trajectories.
method Actor-critic sequence-to-sequence autoencoder with spatial-aware objective function.
result TREP efficiently learns trajectory representations without needing full datasets.

CRAE recommends while learning content sequences, outperforming state-of-the-art methods.

problem Recommendation systems struggle with content information, especially in sequence generation tasks.
method Developed a hybrid denoising recurrent autoencoder (DRAE) for collaborative filtering (CF) that models content sequences.
result CRAE significantly outperforms state-of-the-art methods on recommendation and sequence generation tasks.

New method extracts latent variables from process data using autoencoders.

problem Extracting useful information from diverse, noisy, and nonstandard response processes.
method Sequence-to-sequence autoencoder to compress response processes into standard numerical vectors.
result The latent variables extracted from response processes are useful for understanding complex skills.

This paper explores multi-task sequence learning for better translation quality.

problem Limited exploration of multi-task sequence learning for multiple tasks.
method Three MTL settings: oneto-many, many-to-one, and many-to-many. Examined autoencoder and skip-thought unsupervised objectives.
result Improved translation quality by up to 1.5 BLEU points over single-task baselines.

Improved autoencoder boosts sequence learning with less memory.

problem Training recurrent networks with high memory costs.
method Sparse Predictive Autoencoder (bRSM) with recurrent connections and boosting rule.
result Near optimal performance on stochastic sequence learning task.

daep learns from irregular, multimodal astronomical data.

problem Learning from irregular, multimodal astronomical sequences.
method Diffusion Autoencoder with Perceivers (daep) tokenizes, compresses, and reconstructs data.
result daep outperforms VAE and maep baselines in reconstruction and fine-scale structure preservation.

A new method learns disentangled macro actions from sequences for reinforcement learning.

problem Curse of dimensionality in reinforcement learning action space.
method Autonomously learns disentangled factor representation of actions to generate macro actions.
result Higher scores in complex environments compared to other reinforcement learning algorithms.

Improves supervised learning with target-embedding autoencoders.

problem Improving generalization in purely supervised settings with high-dimensional target spaces.
method Target-Embedding Autoencoders (TEA) for jointly optimizing latent representations for prediction and feature predictability.
result Guaranteed generalization for linear TEAs through uniform stability, and empirical validation across multivariate sequence forecasting.

ES-VAE models skeletal pose trajectories by removing nuisance factors.

problem Handling camera orientation, subject scale, viewpoint, and execution speed in skeletal data.
method ES-VAE uses TSRVF representation on Kendall's shape manifold to isolate shape dynamics.
result ES-VAE outperforms standard VAEs and sequence modeling baselines in gait cycle prediction and action recognition.

CF-VAE models capture multi-modal distributions for better structured sequence prediction.

problem Challenges in capturing multi-modality of future states in latent variable models.
method Conditional Flow Variational Autoencoders (CF-VAE) with conditional normalizing flows.
result CF-VAE achieves state-of-the-art results on multi-modal structured sequence prediction datasets.

A new model improves recurrent neural networks' ability to memorize long sequences.

problem Improving recurrent neural networks' ability to memorize long sequences and extract task-relevant features.
method Proposes a Linear Memory Network with an encoding-based memorization component and a specialized training algorithm.
result Improves the final performance of recurrent neural networks when memorizing long sequences is necessary.

PepCVAE designs novel antimicrobial peptides using a semi-supervised VAE.

problem Designing novel antimicrobial peptides for next-generation antimicrobial resistance solutions.
method Semi-supervised variational autoencoder (VAE) model that learns latent and antimicrobial attribute spaces from unlabeled and labeled data.
result PepCVAE generates novel AMPs with higher long-range diversity and closer to biological peptide distribution.

Paper introduces a novel traffic forecasting model using autoencoders and exogenous variables.

problem Traffic forecasting using aggregated data from vehicles and infrastructure.
method Recurrent Autoencoder with skip connections and exogenous variables for dynamic traffic data.
result Model predicts speed, volume, and traffic direction with exogenous variables like weather and time.

A new method for disentangling action sequences improves model stability.

problem Challenges in unsupervised disentanglement learning due to incomplete theories and abstract notions.
method Introducing disentangling action sequences and a novel fractional variational autoencoder (FVAE) framework.
result FVAE improves the stability of disentanglement for action sequences.

Visual analytics system for comparing medical records using sequence embeddings.

problem Challenges in analyzing medical records due to high dimensionality, irregularity, and sparsity.
method Event and sequence embeddings using autoencoder and self-attention mechanism, with sequence alignment for comparison.
result Demonstrated effectiveness with real-world neonatal ICU dataset.

Improved autoencoders guide latent sentence representations for better text generation and manipulation.

problem Current autoencoders struggle to maintain coherent latent spaces for meaningful text manipulations.
method Adversarial autoencoders with a denoising objective (DAAE) to guide latent space geometry.
result DAAE provides the best trade-off between generation quality and reconstruction capacity.

BART pretrains sequence-to-sequence models by corrupting text and reconstructing it.

problem Improving natural language generation, translation, and comprehension.
method BART uses a denoising autoencoder trained on a Transformer architecture with various noising techniques.
result BART achieves state-of-the-art performance on various NLP tasks with minimal training resources.

Analyze and predict complex 3D shape deformations using LSTM autoencoders and oriented bounding boxes.

problem Detecting and predicting patterns in sequences of deforming 3D shapes.
method Use LSTM autoencoders to create low-dimensional representations of 3D shapes, incorporating oriented bounding boxes for structural components.
result The method detects patterns in plastic deformation and predicts future states of 3D shapes with improved accuracy.

MusicVAE uses a hierarchical decoder to model long-term structure in music sequences.

problem Difficulty of existing recurrent VAE models in modeling long-term structure in sequential data.
method Proposes a hierarchical decoder that outputs embeddings for subsequences and uses these embeddings to generate each subsequence independently.
result Demonstrates better sampling, interpolation, and reconstruction performance than a flat baseline model.

The paper analyzes variational autoencoders for state space models with risk bounds.

problem Analyzing the risk associated with variational autoencoders for state space models.
method Backward factorization of variational distributions to analyze excess risk, providing oracle inequalities and upper bounds.
result Explicit upper bounds on variational estimation error for state space models under strong mixing assumptions.

Model learns disentangled, interpretable representations from sequential data without supervision.

problem Learning disentangled and interpretable representations from sequential data without supervision.
method Factorized hierarchical variational autoencoder with multi-scale priors.
result Model outperforms i-vector baseline in speaker verification and reduces word error rate by 35% in mismatched scenarios.

Piano Genie lets non-musicians improvise on a piano.

problem Improvising on the piano for non-musicians.
method Trained recurrent neural network autoencoders with discrete bottlenecks to learn mappings between user inputs and piano pieces.
result Piano Genie allows users to improvise on the piano with musically meaningful constraints.

Generative Distribution Embeddings learn multiscale representations of distributions.

problem Learning representations of entire distributions for multiscale reasoning.
method Introducing GDE framework that lifts autoencoders to the space of distributions, using conditional generative models and distributional invariance.
result GDEs learn predictive sufficient statistics embedded in Wasserstein space, recovering distances and trajectories for Gaussian and Gaussian mixture distributions.

Diffusion models generate music sequences without autoregressive loops.

problem Generating music sequences from symbolic data using diffusion models.
method Parameterize discrete symbolic data in continuous latent space, train diffusion model, generate sequences through reverse process.
result Strong unconditional generation and post-hoc conditional infilling compared to autoregressive models.

Generative concept representations improve deep learning by handling uncertainty and integrating learning and reasoning.

problem Discriminative deep learning struggles with uncertainty and lacks integration of learning and reasoning.
method Probabilistic and generative deep learning, variational autoencoders, and generative adversarial networks.
result Generative concept representations enhance deep learning by addressing these limitations.