Results 11 to 20 of about 24,500,069 (341)
Generative vs. Non-Generative Models in Engineering Shape Optimization
Journal of Marine Science and EngineeringGenerative models offer design diversity but tend to be computationally expensive, while non-generative models are computationally cost-effective but produce less diverse and often invalid designs. However, the limitations of non-generative models can be
Zahid Masood +4 more
doaj +2 more sources
Elucidating the Design Space of Diffusion-Based Generative Models [PDF]
Neural Information Processing Systems, 2022 We argue that the theory and practice of diffusion-based generative models are currently unnecessarily convoluted and seek to remedy the situation by presenting a design space that clearly separates the concrete design choices.
Tero Karras +3 more
semanticscholar +1 more source
VBench: Comprehensive Benchmark Suite for Video Generative Models [PDF]
Computer Vision and Pattern Recognition, 2023 Video generation has witnessed significant advance-ments, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human ...
Ziqi Huang +15 more
semanticscholar +1 more source
Towards Universal Fake Image Detectors that Generalize Across Generative Models [PDF]
Computer Vision and Pattern Recognition, 2023 With generative models proliferating at a rapid rate, there is a growing need for general purpose fake image detectors. In this work, we first show that the existing paradigm, which consists of training a deep network for real-vs-fake classification ...
Utkarsh Ojha, Yuheng Li, Yong Jae Lee
semanticscholar +1 more source
SneakyPrompt: Jailbreaking Text-to-image Generative Models [PDF]
IEEE Symposium on Security and Privacy, 2023 Text-to-image generative models such as Stable Diffusion and DALL•E raise many ethical concerns due to the generation of harmful images such as Not-Safe-for-Work (NSFW) ones.
Yuchen Yang +4 more
semanticscholar +1 more source
Speech Enhancement and Dereverberation With Diffusion-Based Generative Models [PDF]
IEEE/ACM Transactions on Audio Speech and Language Processing, 2022 In this work, we build upon our previous publication and use diffusion-based generative models for speech enhancement. We present a detailed overview of the diffusion process that is based on a stochastic differential equation and delve into an extensive
Julius Richter +4 more
semanticscholar +1 more source
DiffusionDB: A Large-scale Prompt Gallery Dataset for Text-to-Image Generative Models [PDF]
Annual Meeting of the Association for Computational Linguistics, 2022 With recent advancements in diffusion models, users can generate high-quality images by writing text prompts in natural language. However, generating images with desired details requires proper prompts, and it is often unclear how a model reacts to ...
Zijie J. Wang +5 more
semanticscholar +1 more source
Is synthetic data from generative models ready for image recognition? [PDF]
International Conference on Learning Representations, 2022 Recent text-to-image generation models have shown promising results in generating high-fidelity photo-realistic images. Though the results are astonishing to human eyes, how applicable these generated images are for recognition tasks remains under ...
Ruifei He +7 more
semanticscholar +1 more source
Leveraging Passage Retrieval with Generative Models for Open Domain Question Answering [PDF]
Conference of the European Chapter of the Association for Computational Linguistics, 2020 Generative models for open domain question answering have proven to be competitive, without resorting to external knowledge. While promising, this approach requires to use models with billions of parameters, which are expensive to train and query.
Gautier Izacard, Edouard Grave
semanticscholar +1 more source
Self-Consuming Generative Models Go MAD [PDF]
International Conference on Learning Representations, 2023 Seismic advances in generative AI algorithms have led to the temptation to use AI-synthesized data to train next-generation models. Repeating this process creates autophagous (“self-consuming”) loops whose properties are poorly understood.
Sina Alemohammad +7 more
semanticscholar +1 more source