Pros and cons of GAN evaluation measures: New developments

A Borji - Computer Vision and Image Understanding, 2022 - Elsevier
This work is an update of my previous paper on the same topic published a few years ago
(Borji, 2019). With the dramatic progress in generative modeling, a suite of new quantitative …

Denoising diffusion implicit models

J Song, C Meng, S Ermon - arxiv preprint arxiv:2010.02502, 2020 - arxiv.org
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image
generation without adversarial training, yet they require simulating a Markov chain for many …

Understanding deep learning (still) requires rethinking generalization

C Zhang, S Bengio, M Hardt, B Recht… - Communications of the …, 2021 - dl.acm.org
Despite their massive size, successful deep artificial neural networks can exhibit a
remarkably small gap between training and test performance. Conventional wisdom …

Automated and autonomous experiments in electron and scanning probe microscopy

SV Kalinin, M Ziatdinov, J Hinkle, S Jesse, A Ghosh… - ACS …, 2021 - ACS Publications
Machine learning and artificial intelligence (ML/AI) are rapidly becoming an indispensable
part of physics research, with domain applications ranging from theory and materials …

How generative AI models such as ChatGPT can be (mis) used in SPC practice, education, and research? An exploratory study

FM Megahed, YJ Chen, JA Ferris, S Knoth… - Quality …, 2024 - Taylor & Francis
Abstract Generative Artificial Intelligence (AI) models such as OpenAI's ChatGPT have the
potential to revolutionize Statistical Process Control (SPC) practice, learning, and research …

Trojdiff: Trojan attacks on diffusion models with diverse targets

W Chen, D Song, B Li - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
Diffusion models have achieved great success in a range of tasks, such as image synthesis
and molecule design. As such successes hinge on large-scale training data collected from …

Convergence of denoising diffusion models under the manifold hypothesis

V De Bortoli - arxiv preprint arxiv:2208.05314, 2022 - arxiv.org
Denoising diffusion models are a recent class of generative models exhibiting state-of-the-
art performance in image and audio synthesis. Such models approximate the time-reversal …

Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and dall-e 2

A Borji - arxiv preprint arxiv:2210.00586, 2022 - arxiv.org
The field of image synthesis has made great strides in the last couple of years. Recent
models are capable of generating images with astonishing quality. Fine-grained evaluation …

Supporting human-ai collaboration in auditing llms with llms

C Rastogi, M Tulio Ribeiro, N King, H Nori… - Proceedings of the 2023 …, 2023 - dl.acm.org
Large language models (LLMs) are increasingly becoming all-powerful and pervasive via
deployment in sociotechnical systems. Yet these language models, be it for classification or …

Iti-gen: Inclusive text-to-image generation

C Zhang, X Chen, S Chai, CH Wu… - Proceedings of the …, 2023 - openaccess.thecvf.com
Text-to-image generative models often reflect the biases of the training data, leading to
unequal representations of underrepresented groups. This study investigates inclusive text …