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.

168,695 papers · 148 categories

Trend · papers per month

165330494659 · Jun 202019922001200920172026
48 results for enhanced states

Diffusion models enhance speech without supervision.

problem Challenges in generalizing supervised speech enhancement methods to unseen conditions.
method Unsupervised speech enhancement using diffusion-based generative models.
result Demonstrates promising results compared to supervised and unsupervised baselines.

OTRE uses OT to improve retinal images, outperforming existing methods.

problem Improving quality of non-mydriatic retinal images for accurate diagnoses.
method OT theory for image-to-image translation, regularization by enhancing.
result OTRE outperforms state-of-the-art methods on various retinal image tasks.

Enhances RL in partially observable, noisy environments by uncovering causal states.

problem Making decisions based on incomplete and noisy observations in partially observable Markov decision processes (P2^2OMDPs).
method Causal State Representation under Asynchronous Diffusion Model (CaDiff) framework, incorporating a novel asynchronous diffusion model (ADM) and a new bisimulation metric.
result Enhances returns by at least 14.18% compared to baselines on Roboschool tasks.

Enhances 2D face recognition with 3D features using active illumination.

problem Improving robustness of 2D face recognition to spoofing attacks and low-light conditions.
method Projecting a high spatial frequency pattern onto the face to recover 3D information and a 2D image simultaneously.
result Significantly boosts face recognition performance and dramatically improves robustness to spoofing attacks.

Current state-of-the-art discrete optimization methods struggle behind when it comes to challenging contrast-enhancing discrete energies (i.e., favoring different labels for neighboring variables). This work suggests a multiscale approach for these challenging problems. Deriving an algebraic representation allows us to…

2012-10-26abs ↗pdf ↗

Enhances particle filters with neural augmentation for multi-sub-state tracking.

problem Particle filters struggle with complex or approximated models and low latency requirements.
method Learning Flock (LF) uses a neural network to correct particle weights based on sub-particle relationships.
result LF improves performance, robustness, and latency in radar multi-target tracking.

In this short survey article we collect the current state of the art in the nascent field of \textit{quantum enhancements}, a type of knot invariant defined by collecting values of quantum invariants of knots with colorings by various algebraic objects over the set of such colorings. This class of invariants includes c…

2018-05-30abs ↗pdf ↗

Speech enhancement improved by adapting to unknown speakers without auxiliary signals.

problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.

This paper tackles unsupervised speech enhancement using RVAE and proposes efficient sampling methods.

problem Unsupervised speech enhancement with high computational complexity.
method Recurrent variational autoencoder (RVAE) combined with Langevin dynamics and Metropolis-Hasting sampling.
result Sampling-based algorithms outperform VEM and achieve robust generalization.

RDL-Net improves speech enhancement with fewer parameters and better performance.

problem Improving speech enhancement with fewer parameters and better performance.
method Proposes RDL-Net, a CNN combining residual and dense aggregations without over-allocating parameters.
result RDL-Net achieves higher speech enhancement performance with fewer parameters and lower computational requirements.

FEDformer combines Transformer with seasonal-trend decomposition for efficient long-term forecasting.

problem Transformer's inefficiency and inability to capture global time series views.
method Combines seasonal-trend decomposition with Transformer, exploiting Fourier basis for frequency enhancement.
result Reduces prediction error by 14.8% and 22.6% for multivariate and univariate time series, respectively.

Enhanced time series forecasting with improved trend and seasonal components.

problem Challenges in real-world time series forecasting, especially in multivariate applications.
method Individual decomposition of trend and seasonal components, using different approaches for each.
result Significant reduction in error values, around 10% MSE average reduction across benchmarks.

We present a novel approach to adjust global image properties such as colour, saturation, and luminance using human-interpretable image enhancement curves, inspired by the Photoshop curves tool. Our method, dubbed neural CURve Layers (CURL), is designed as a multi-colour space neural retouching block trained jointly in…

2019-11-29abs ↗pdf ↗

TK-GCN forecasts spatiotemporal dynamics using Koopman-enhanced graph convolutional networks.

problem Forecasting complex spatiotemporal dynamics over irregular domains.
method Two-stage framework: Koopman-enhanced Graph Convolutional Network (K-GCN) for spatial encoding and Transformer for temporal modeling.
result TK-GCN outperforms state-of-the-art methods in spatiotemporal cardiac dynamics forecasting.

Enhanced ensemble filters use machine learning to improve accuracy in filtering models.

problem Accuracy limitations of traditional ensemble Kalman filters.
method Introduces a measure neural mapping (MNM) to map joint predicted state and observation to updated state estimates.
result Superior root-mean-square-error performance compared to leading methods in filtering models.

Real-time speech enhancement model removes various noises and reverb.

problem Real-time speech enhancement in noisy environments.
method Causal speech enhancement model using encoder-decoder architecture with skip-connections, optimized in time and frequency domains.
result The model matches state-of-the-art performance while working directly on raw waveform.

Paper enhances haptic signals distinguishability with boosted technique.

problem Lack of large datasets in haptics domain limits feature extraction.
method General framework for haptic signal analysis, using spectral features and boosted embedding.
result Framework needs less training data and outperforms state-of-the-art.

Given a connect sum of link diagrams, there is an isomorphism which decomposes unnormalized Khovanov chain groups for the product in terms of normalized chain groups for the factors; this isomorphism is straightforward to see on the level of chains. Similarly, any plumbing xyx*y of Kauffman states carries an isomorphis…

2017-05-04abs ↗pdf ↗

A reinforcement learning approach prepares quantum squeezed states in open spin systems.

problem Generating non-classical states in open quantum systems with dissipation and dephasing.
method Reinforcement learning to determine optimal control pulses for spin-squeezing.
result Optimal control sequences enhance collective spin squeezing and entanglement.

Enhances ZSL models with biologically inspired feature enhancement.

problem Limited training data leads to poor feature extraction from pre-trained models.
method Dual-channel learning framework using auxiliary data sets.
result Improves ZSL model's generalization ability and achieves state-of-the-art results.

Enhances few-shot image classification using unlabelled examples.

problem Few-shot image classification with limited labeled data.
method Transductive meta-learning combining soft k-means clustering and neural feature extractor.
result State-of-the-art performance on Meta-Dataset, mini-ImageNet, and tiered-ImageNet benchmarks.

Quaternion Conformer GAN (QC-GAN) is a parameter-efficient speech enhancement framework that combines a Quaternion Conformer generator with MetricGAN-based training.

problem Speech Enhancement
method Quaternion Conformer GAN
result Achieved a PESQ score of 3.48 with 0.89M parameters, comparable to state-of-the-art models at less than half their size.

Enhanced Hopfield model boosts memory retrieval capacity.

problem Memory retrieval in modern Hopfield models with limited capacity.
method Introduces a learnable feature map transforming energy function into kernel space, minimizing separation loss for uniform memory distribution.
result Significant reduction in metastable states, enhancing memory capacity and retrieval accuracy.

Stabilizes training of DNN for speech enhancement using PESQ scores.

problem Stability issues in training DNNs using non-differentiable OSQA scores.
method Approximate OSQA scores with a differentiable auxiliary DNN and stabilize training with reinforcement learning techniques.
result Stable training of DNN to achieve state-of-the-art PESQ scores and better sound quality.

TinyLSTMs reduces speech enhancement model size and latency for hearing aids.

problem Large RNNs limit practical deployment in hearing aid hardware.
method Model compression techniques (pruning, integer quantization, state update skipping) for RNN speech enhancement.
result Reduction in model size and operations by 11.9imes imes and 2.9imes imes, respectively, without perceptual degradation.

Enhanced ECCD speeds up elastic net model training.

problem Efficiently solving generalized linear models with elastic net constraints.
method Redesigned cyclic coordinate descent with Taylor expansion and batched computations.
result Empirically shows consistent 3imes3 imes performance improvement over state-of-the-art solvers.

Enhanced SMC2^2 uses gradients from CRN-PF in Langevin proposals for improved state and parameter estimation.

problem Challenges in high-dimensional parameter spaces for SMC2^2.
method Leveraging gradients from a CRN-PF within a Langevin proposal.
result Higher effective sample size and more accurate parameter estimates.

In the current era of neural networks and big data, higher dimensional data is processed for automation of different application areas. Graphs represent a complex data organization in which dependencies between more than one object or activity occur. Due to the high dimensionality, this data creates challenges for mach…

2019-12-19abs ↗pdf ↗

Report on enhancing trust in ML models with visualizations.

problem Understanding and trusting the results of black box ML models.
method Categorization of visualization techniques, statistical overview, topic analyses, and interactive web-based survey.
result Expanded categorization of trust against different facets of interactive ML.

Most deep learning-based models for speech enhancement have mainly focused on estimating the magnitude of spectrogram while reusing the phase from noisy speech for reconstruction. This is due to the difficulty of estimating the phase of clean speech. To improve speech enhancement performance, we tackle the phase estima…

2019-03-07abs ↗pdf ↗

Paper presents a deep learning framework for faster, more accurate nuclear reactor power prediction.

problem Inaccurate and inefficient modeling of nuclear reactor transients.
method Hybrid digital twin-focused multi-stage deep learning framework using feed-forward neural networks.
result Achieved remarkable accuracy (96% classification, 2.3% MAPE) with noise-enhanced simulated data.

TSSC images enhance chaotic signal classification using ConvNets.

problem Classifying chaotic signals accurately and robustly.
method Triad State Space Construction (TSSC) for image encoding, Convolutional Neural Network (ConvNet) for classification.
result TSSC-ConvNet achieves high accuracy and robustness in chaotic signal classification.