AI Briefing#diffusion-model
The latest AI and developer news about #diffusion-model, with the original source and a short summary.
The latest AI and developer news about #diffusion-model, with the original source and a short summary.
This introduces generative models and SDE-based Score-based Generative Modeling, key trends at ICLR 2021.
This piece analyzes the principles of Diffusion Models, a core component of generative models, and the differences among various generative models.
This review focuses on the Diffusion Model, one of the most-noticed generative models among the diverse works presented at NeurIPS 2021, and covers the key research on it.
Introduces the latest research trends in generative models (SGM) and LLMs presented at NeurIPS 2022.
LG AI Research reviewed major research trends in generative models, LLMs, and reinforcement learning presented at NeurIPS 2022.
LG AI Research proposed an OOD detection methodology that generates sophisticated synthetic outliers using a Diffusion model.
This post analyzes the research trends in architecture and downstream tasks for Score-based Generative Modeling presented at NeurIPS 2023.
LG AI Research unveiled research that improves OOD detection performance by generating sophisticated synthetic outliers using a Diffusion model.
This piece looks at research trends in the architecture and downstream tasks of score-based generative models presented at NeurIPS 2023.
It introduces the 'Generative Image Dynamics' research, selected as Best Paper at CVPR 2024, a technology that generates natural motion from still images.
LG AI Research presented CADO research at ICML 2024, combining reinforcement learning and diffusion models to solve combinatorial optimization problems.
LG AI Research presented CADO, a study combining diffusion models with reinforcement learning to solve combinatorial optimization problems, at ICML 2024.
LG AI Research proposed Projection Regret, a technique that leverages Diffusion models to reduce interference from background information and improve novelty detection performance.
LG AI Research proposed Projection Regret, a technique that uses a Diffusion model to reduce background noise and improve anomaly detection performance.
LG AI Research has unveiled SONA, a new OOD detection framework that uses diffusion models to precisely control semantic features.
LG AI Research has developed SONA, a framework that leverages Diffusion models to precisely generate Near-OOD data.
LG AI Research has unveiled the SciNO framework, which enables stable causal discovery even in high-dimensional data environments.
LG AI Research has unveiled the SciNO framework, which supports stable causal relationship inference even in high-dimensional data.
The paper proposes the FAE framework, which uses only a single attention layer to transform pretrained visual representations into a low-dimensional latent space suitable for image generation.
GenCeption is proposed as a general-purpose vision model that performs diverse visual cognition tasks by leveraging video generation models.
Wan-Dancer, a model that generates high-quality dance videos over 1 minute long in sync with music rhythm, has been released.
PixWorld is a unified diffusion model that performs 3D generation and reconstruction simultaneously in pixel space without a VAE.
MrFlow has been proposed as a technology that dramatically speeds up the inference of Diffusion models through step-wise resolution adjustment without additional training.
A technique is proposed that maximizes the efficiency of Diffusion-based Speculative Decoding by predicting the optimal block size according to the input data.