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.

168,657 papers · 148 categories

Trend · papers per month

3537061,0581,411 · Jun 202019922001200920172026
48 results for model synthesis

The recent success of raw audio waveform synthesis models like WaveNet motivates a new approach for music synthesis, in which the entire process --- creating audio samples from a score and instrument information --- is modeled using generative neural networks. This paper describes a neural music synthesis model with fl…

2018-11-01abs ↗pdf ↗

Language models predict inorganic synthesis conditions and temperatures.

problem Limited data and heuristic approaches constrain inorganic synthesis planning.
method Language models without fine-tuning predict precursor conditions and temperatures.
result Language models achieve high accuracy in predicting synthesis conditions and temperatures.

AutoDiff combines auto-encoder and diffusion model for realistic tabular data synthesis.

problem Generating realistic synthetic tabular data with heterogeneous features.
method Employing auto-encoder architecture to handle tabular data's complexity.
result Synthetic tables from AutoDiff show good statistical fidelity and perform well in machine learning tasks.

CrossBeam learns to search more efficiently in program synthesis.

problem Efficiently searching through vast program spaces.
method Trains a neural model to guide program synthesis, combining previously explored programs.
result CrossBeam explores much smaller portions of the program space compared to state-of-the-art methods.

Coupling the high-fidelity generation capabilities of label-conditional image synthesis methods with the flexibility of unconditional generative models, we propose a semantic bottleneck GAN model for unconditional synthesis of complex scenes. We assume pixel-wise segmentation labels are available during training and us…

2019-11-26abs ↗pdf ↗

Model for directed synthesis of audio textures using multi-scale RNNs.

problem Challenges in modeling complex audio textures with traditional methods.
method Combining multi-scale RNNs with a conditioning strategy for user-directed synthesis.
result Demonstrated improved performance on various audio texture datasets.

InVAErt networks use data-driven methods for system synthesis and identifiability analysis.

problem Model synthesis and identifiability analysis for complex systems.
method Deterministic encoder and decoder, normalizing flow, variational encoder, loss function penalty coefficients, latent space sampling.
result Validation through various system types, demonstrating effectiveness of the framework.

We present a program synthesis-oriented dataset consisting of human written problem statements and solutions for these problems. The problem statements were collected via crowdsourcing and the program solutions were extracted from human-written solutions in programming competitions, accompanied by input/output examples…

2018-07-06abs ↗pdf ↗

Improved texture synthesis using wavelet-based statistics with rectifier non-linearity.

problem Improving texture synthesis quality using wavelet representations.
method Proposes a family of statistics based on non-linear wavelet representations with a generalized rectifier non-linearity.
result Significantly improves visual quality of texture synthesis compared to classical wavelet-based models.

In this paper we demonstrate speech synthesis using different electroencephalography (EEG) feature sets recently introduced in [1]. We make use of a recurrent neural network (RNN) regression model to predict acoustic features directly from EEG features. We demonstrate our results using EEG features recorded in parallel…

2020-02-22abs ↗pdf ↗

Proposes a synthesis algorithm using Conformal Prediction for improved Deep Learning performance.

problem Assessing the quality of synthesised data for high-stake domains.
method Conformal Prediction framework for generating data from high-confidence feature space regions.
result Training sets extended with confident synthesised data improved Deep Learning performance by up to 61 percentage points F1-score.

Generative adversarial networks (GANs) are a recent approach to train generative models of data, which have been shown to work particularly well on image data. In the current paper we introduce a new model for texture synthesis based on GAN learning. By extending the input noise distribution space from a single vector …

2016-11-24abs ↗pdf ↗

A new TTS method uses diffusion and VAE for better speech synthesis.

problem Improving text-to-speech synthesis for better speech quality and robustness.
method Combines diffusion probabilistic model and variational autoencoder for latent variable conversion.
result The method is robust to poor orthography and alignment errors.

MEGAN models chemical reactions as graph edits, improving synthesis planning.

problem Generating and predicting chemical reactions under constraints.
method End-to-end encoder-decoder neural model inspired by arrow pushing formalism.
result State-of-the-art accuracy in standard benchmarks for retrosynthesis prediction.

High-quality image synthesis with diffusion models, achieving state-of-the-art FID score.

problem Generating high-quality images from latent variables.
method Training diffusion probabilistic models with a weighted variational bound, inspired by denoising score matching and Langevin dynamics.
result State-of-the-art FID score of 3.17 on CIFAR10 dataset.

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

problem Lack of large-scale 3D datasets and efficient architectures for 3D synthesis.
method Adapting a 2D diffusion model to 3D synthesis using a loss based on probability density distillation.
result A 3D model can be optimized from a 2D diffusion model, allowing for text-to-3D synthesis.

Improved generative models using critically-damped Langevin diffusion.

problem Current score-based generative models (SGMs) use overly simplistic diffusion processes, leading to complex denoising tasks and suboptimal performance.
method Proposed a novel critically-damped Langevin diffusion (CLD) and derived a score matching objective and sampling scheme.
result CLD-based SGMs achieve superior performance in synthesis quality compared to previous methods.

Improved diffusion models for image synthesis with better training dynamics.

problem Uneven and ineffective training in diffusion models.
method Redesigned network layers to preserve activation, weight, and update magnitudes.
result Significantly better networks at equal computational complexity, improving FID to 1.81.

New method allows real-time audio synthesis using non-causal convolutions.

problem Real-time audio synthesis limitations due to offline model constraints.
method Post-training reconfiguration of non-causal models for real-time buffer-based processing.
result Non-causal streaming models can be transformed from offline-trained models without quality loss.

Inverse Drum Machine separates drum mixes using transcription and synthesis.

problem Separating individual drum tracks from mixed recordings.
method Analysis-by-synthesis framework combining deep learning and automatic transcription.
result Separation quality comparable to supervised methods requiring isolated stems.

Generative models of natural images have progressed towards high fidelity samples by the strong leveraging of scale. We attempt to carry this success to the field of video modeling by showing that large Generative Adversarial Networks trained on the complex Kinetics-600 dataset are able to produce video samples of subs…

2019-07-15abs ↗pdf ↗

Novel unsupervised random forests improve density estimation and data synthesis.

problem Density estimation and data synthesis for complex tabular data.
method Recursive unsupervised random forests with alternating generation and discrimination rounds.
result Provable consistency and smooth densities with fast execution.

Programming-by-example (PBE) is a synthesis paradigm that allows users to generate functions by simply providing input-output examples. While a promising interaction paradigm, synthesis is still too slow for realtime interaction and more widespread adoption. Existing approaches to PBE synthesis have used automated reas…

2020-02-07abs ↗pdf ↗

WeSinger improves singing voice synthesis with data augmentation and specialized modules.

problem Improving the accuracy and naturalness of synthesized singing voices.
method Developed a multi-singer Chinese neural singing voice synthesis system with deep bi-directional LSTM, Transformer, LPCNet, and data augmentation.
result WeSinger achieves state-of-the-art performance on the Opencpop corpus.

PriorGrad improves speech synthesis models by using data-dependent adaptive priors.

problem Inefficiency in denoising diffusion models due to mismatch between prior and data distributions.
method Proposes PriorGrad, an adaptive prior derived from data statistics based on conditional information.
result PriorGrad achieves faster convergence and superior performance in speech synthesis models.