Survey on GANs for generating visual arts, music, and literature.
problem Tackles the challenge of generating art using GANs.
method Uses generative adversarial networks (GANs) to generate visual arts, music, and literary text.
result Performance comparison and description of various GAN architectures presented.
Simple ML models generate art completions.
problem Creating art through machine learning.
method Single-output classification and regression models trained on various image datasets.
result Generated images complete missing parts of input images.
Uses art composition attributes to guide CycleGAN image translation.
problem Improving image-to-image translation quality.
method Trained ACAN on art composition attributes to influence CycleGAN.
result CycleGAN translations improved with ACAN constraints.
CGANs forecast art movements by generating sequences of paintings.
problem Predicting the evolution of art movements over time.
method Trained CGANs on sequences of paintings, using VAR models for forecasting.
result CGANs accurately predict future art movements and generate plausible paintings.
AI generates sculptural objects through machine learning.
problem Generating creative and printable 3D sculptures.
method Developed two algorithms: Amalgamated DeepDream (ADD) and Partitioned DeepDream (PDD).
result Generated creative and printable 3D point clouds.
Synthesizes AI and human creativity for more compelling art.
problem Making AI-generated art more human-like.
method Combining Deep Learning and Cognitive Psychology theories.
result Demonstrates how AI can incorporate human creativity theories.
ART improves transfer learning performance with robust theory and methods.
problem Improving performance of primary tasks using auxiliary data.
method Adaptive Robust Transfer Learning (ART) pipeline with theoretical guarantees.
result ART provides a provable theoretical guarantee for adaptive transfer and robustness.
This paper presents a new multitask learning framework that learns a shared representation among the tasks, incorporating both task and feature clusters. The jointly-induced clusters yield a shared latent subspace where task relationships are learned more effectively and more generally than in state-of-the-art multitas…
Survey of ART neural networks for engineering applications.
problem Understanding and utilizing ART neural networks for various machine learning tasks.
method Comprehensive review of classic and modern ART models, describing learning dynamics and engineering properties.
result Compilation of ART models and their properties for engineering applications.
Unified model for sequence labeling and classification.
problem Efficiently perform multiple sequence labeling tasks.
method Generative framework with shared natural language output space.
result Significant improvements in few-shot and low-resource slot labeling.
Generative models learn complex spatial patterns using program synthesis.
problem Capturing complex global structure in data, especially in images.
method Incorporates programs representing global structure into generative models and learns these models through program synthesis.
result Significantly better at generating and completing images with global structure compared to state-of-the-art methods.
Residual networks (ResNets) have recently achieved state-of-the-art on challenging computer vision tasks. We introduce Resnet in Resnet (RiR): a deep dual-stream architecture that generalizes ResNets and standard CNNs and is easily implemented with no computational overhead. RiR consistently improves performance over R…
Normalizing flows and autoregressive models have been successfully combined to produce state-of-the-art results in density estimation, via Masked Autoregressive Flows (MAF), and to accelerate state-of-the-art WaveNet-based speech synthesis to 20x faster than real-time, via Inverse Autoregressive Flows (IAF). We unify a…
Paper improves ATN for generating adversarial examples.
problem Generating adversarial examples to fool models.
method Improves Adversarial Transformation Networks (ATN).
result Won 2nd place in CAAD 2018 non-target task.
Deep generative models parameterized by neural networks have recently achieved state-of-the-art performance in unsupervised and semi-supervised learning. We extend deep generative models with auxiliary variables which improves the variational approximation. The auxiliary variables leave the generative model unchanged b…
This paper benchmarks speech LVMs against deterministic models and adapts a video model to speech.
problem Speech generation models are inferior to deterministic models.
method Developed a speech benchmark of LVMs and compared them against deterministic models.
result The Clockwork VAE outperforms previous LVMs and reduces the gap to deterministic models.
Paper introduces Arte-Blue Chip Index for diversifying portfolios with art investments.
problem Evaluating blue-chip art as a viable asset class for diversification.
method Developed Arte-Blue Chip Index tracking top-performing artists over 24 years.
result 20% allocation of blue-chip art in a diversified portfolio increases risk-adjusted returns by 20%.
RFN improves GCNs for road networks, outperforming state-of-the-art by 21%-40%.
problem Leveraging the structure of road networks effectively in machine learning tasks.
method Introducing RFN, a novel GCN specifically designed for road networks.
result RFN outperforms state-of-the-art GCNs by 21%-40% on road network tasks.
KaoKore dataset extracts faces from pre-modern Japanese art for machine learning.
problem Lack of relevant datasets for historical Japanese artworks in machine learning.
method Extracted faces from pre-modern Japanese artwork to create a new dataset.
result Demonstrated the dataset's value for image classification and creative applications.
Computer graphics techniques improve art pricing by measuring painting effort.
problem Traditional art pricing models lack measures for conceptual and painting efforts.
method Applied image recognition to measure line and color variances as proxies for effort.
result Painting effort (line and color variances) significantly positively correlates with sales price.
I-BERT extends Transformer's self-attention to arbitrary input lengths.
problem Transformer models struggle with inductive generalization to unseen input lengths.
method Replaces positional encodings with a recurrent layer.
result I-BERT achieves state-of-the-art results on algorithmic tasks.
Combines RNNs and tensor products for sequential data, outperforming state-of-the-art.
problem Improving symbolic interpretation and systematic generalization in natural language reasoning.
method End-to-end training of a recurrent neural network architecture with tensor product representations.
result Significantly outperforms state-of-the-art models in natural language reasoning tasks.
Bonsai-Net efficiently discovers state-of-the-art models with fewer parameters.
problem Efficiently discovering state-of-the-art neural architectures with minimal computational expense.
method Bonsai-Net uses a modified differential pruner to explore a relaxed search space.
result Bonsai-Net consistently discovers better architectures than random search with fewer parameters.
New model improves image captioning's ability to describe unseen concepts.
problem Image captioning models struggle with describing unseen combinations of concepts.
method Proposes a multi-task model combining caption generation and image-sentence ranking, with a decoding mechanism to re-rank captions based on image similarity.
result The model significantly outperforms state-of-the-art models in compositional generalization.
Recently, deep learning has been applied to many security-sensitive applications, such as facial authentication. The existence of adversarial examples hinders such applications. The state-of-the-art result on defense shows that adversarial training can be applied to train a robust model on MNIST against adversarial exa…
BCD-Net improves low-dose CT image reconstruction.
problem Challenges in obtaining accurate low-dose CT images.
method Modified iterative regression CNN, BCD-Net, with faster numerical solvers.
result BCD-Net achieves better image quality and generalization than state-of-the-art methods.
Automatically jailbreaks LLMs with black-box access.
problem Generating harmful content from black-box LLMs.
method Automated method using an attacker LLM to refine prompts.
result Generates jailbreaks for over 80% of prompts.
AI recovers lost art from x-rays.
problem Reconstructing lost artwork under layers of x-ray imaging.
method Neural style transfer applied to x-radiographs.
result Reconstructed lost artwork visible through x-rays.
A new method uses compressive autoencoders for image restoration.
problem Efficient regularization of inverse problems in computational imaging.
method Variational Bayes Latent Estimation (VBLE) with compressive autoencoders.
result VBLE achieves similar performance to state-of-the-art PnP methods but faster.
Wasserstein GAN improves anomaly detection on time series data.
problem Anomaly detection in time series datasets.
method Wasserstein GAN for learning normal data distribution and anomaly detection using a stacked encoder.
result W-GAN with encoder achieves state-of-the-art anomaly detection scores on MNIST and multi-variate time series.
Study examines fake news as modern myths using AI.
problem Misinformation and propaganda in fake news.
method Machine learning to generate fake articles.
result Details of fake news generation pipeline.
BigBiGAN improves unsupervised representation learning using image generation quality.
problem Improving unsupervised representation learning methods.
method Extending BigGAN to include an encoder and modifying the discriminator for representation learning.
result BigBiGAN models achieve state-of-the-art performance in unsupervised representation learning and unconditional image generation.
GOAD improves anomaly detection across various data types.
problem Finding anomalies in diverse data types.
method GOAD combines classification and transformation-based methods.
result GOAD achieves state-of-the-art accuracy on multiple datasets.
New method generates fast adversarial faces with high success rate.
problem Vulnerability of face recognition systems to adversarial attacks.
method Fast landmark manipulation method and semantic structure constrained attack.
result 99.86% success rate on state-of-the-art face recognition models.
Universal adversarial patches prevent face detection in various frameworks.
problem Preventing face detection in state-of-the-art face detection systems.
method Investigated the phenomenon of patches that suppress face detection and proposed optimization-based approaches for automatic design.
result Universal adversarial patches can prevent face detection without introducing false positives.
New neural network layer handles OOV words in NLP tasks without pre-training.
problem Handling out-of-vocabulary words in natural language processing.
method Contextual-compositional neural network layer that attends to character sequence and context.
result Improves performance on 23 languages in joint tagging tasks.
Deep learning has shown promising results on many machine learning tasks but DL models are often complex networks with large number of neurons and layers, and recently, complex layer structures known as building blocks. Finding the best deep model requires a combination of finding both the right architecture and the co…
NFTs revolutionize art sales by providing proof of ownership.
problem Lack of provenance and authenticity in digital art.
method Analysis of major art NFT marketplaces.
result NFTs reduce the need for intermediaries in the art trade.
In this paper, we present Paranom, a parallel anomaly dataset generator. We discuss its design and provide brief experimental results demonstrating its usefulness in improving the classification correctness of LSTM-AD, a state-of-the-art anomaly detection model.
This paper introduces a new financial metric for the art market. The metric is based on the price per unit of area and is applicable to two-dimensional art objects such as paintings.
Improved image compression with diffusion models outperforming state-of-the-art methods.
problem Difficulties in replicating text-to-image success in image compression.
method Two-stage approach combining autoencoder targeting MSE followed by score-based decoder.
result Significantly improved perceptual quality at a given bit-rate, measured by FID score.
NFT art market shows strong preferential ties among sellers and buyers.
problem Reducing preferential ties in NFT art market.
method Analyzing NFT art sales data from multiple galleries.
result NFT art market is highly concentrated with preferential ties.
DDVFA learns and retrieves clusters without order dependence, outperforming other methods.
problem Order dependence in clustering methods.
method DDVFA combines distributed higher-order activation and match functions with dual vigilance parameters.
result DDVFA outperforms other clustering methods in online learning mode.
Deep generative models have been praised for their ability to learn smooth latent representation of images, text, and audio, which can then be used to generate new, plausible data. However, current generative models are unable to work with molecular graphs due to their unique characteristics-their underlying structure …
Generative model produces high-fidelity video samples.
problem Generating high-fidelity videos from complex datasets.
method Large GAN trained on Kinetics-600 dataset, using a computationally efficient discriminator.
result Achieved state-of-the-art metrics in video synthesis and prediction.
Improved image generation with fewer labels.
problem Generating high-fidelity images with limited labeled data.
method Self- and semi-supervised learning techniques.
result Outperforms state-of-the-art models using 10-20% of labels.
Raven's Progressive Matrices are one of the widely used tests in evaluating the human test taker's fluid intelligence. Analogously, this paper introduces geometric generalization based zero-shot learning tests to measure the rapid learning ability and the internal consistency of deep generative models. Our empirical re…
Set Flow models sets of data, learns dependencies, and achieves state-of-the-art likelihoods.
problem Modeling and sampling from finite, potentially high-dimensional, non-i.i.d. sets of data.
method Extends RealNVPs to handle finite sets, maintaining invertibility and exact log-likelihood evaluation.
result Achieves state-of-the-art likelihoods on 3D point clouds.