Imprint: Generative object compositing by learning identity-preserving representation

Y Song, Z Zhang, Z Lin, S Cohen… - Proceedings of the …, 2024 - openaccess.thecvf.com
Generative object compositing emerges as a promising new avenue for compositional
image editing. However the requirement of object identity preservation poses a significant …

[PDF][PDF] Enhancing gastrointestinal diagnostics with yolo-based deep learning techniques

Y Yang, Y Jin, Q Tian, Y Yang, W Qin, X Ke - 2024 - preprints.org
Gastrointestinal (GI) tract disorders, ranging from benign polyps to aggressive forms of
cancer, pose significant health challenges globally. Early detection and precise …

Inverse uncertainty quantification by hierarchical bayesian modeling and application in nuclear system thermal-hydraulics codes

C Wang, X Wu, T Kozlowski - arXiv preprint arXiv:2305.16622, 2023 - arxiv.org
Inverse Uncertainty Quantification (IUQ) method has been widely used to quantify the
uncertainty of Physical Model Parameters (PMPs) in nuclear Thermal Hydraulics (TH) …

Towards Dataset-scale and Feature-oriented Evaluation of Text Summarization in Large Language Model Prompts

S Yu-Te Lee, A Bahukhandi, D Liu… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recent advancements in Large Language Models (LLMs) and Prompt Engineering have
made chatbot customization more accessible, significantly reducing barriers to tasks that …

LLMExplainer: Large Language Model based Bayesian Inference for Graph Explanation Generation

J Zhang, J Liu, D Luo, J Neville, H Wei - arXiv preprint arXiv:2407.15351, 2024 - arxiv.org
Recent studies seek to provide Graph Neural Network (GNN) interpretability via multiple
unsupervised learning models. Due to the scarcity of datasets, current methods easily suffer …

Many-Shot In-Context Learning in Multimodal Foundation Models

Y Jiang, J Irvin, JH Wang, MA Chaudhry… - arXiv preprint arXiv …, 2024 - arxiv.org
Large language models are well-known to be effective at few-shot in-context learning (ICL).
Recent advancements in multimodal foundation models have enabled unprecedentedly …

Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation

L He, Y Song, H Huang, D Aliaga, X Zhou - arXiv preprint arXiv …, 2024 - arxiv.org
Text-to-video generation has been dominated by end-to-end diffusion-based or
autoregressive models. On one hand, those novel models provide plausible versatility, but …

Refine-by-Align: Reference-Guided Artifacts Refinement through Semantic Alignment

Y Song, L He, Z Zhang, SY Kim, H Zhang… - arXiv preprint arXiv …, 2024 - arxiv.org
Personalized image generation has emerged from the recent advancements in generative
models. However, these generated personalized images often suffer from localized artifacts …

Prompt Optimizer of Text-to-Image Diffusion Models for Abstract Concept Understanding

Z Fan, X Li, K Nag, C Fang, T Biswas, J Xu… - … Proceedings of the ACM …, 2024 - dl.acm.org
The rapid evolution of text-to-image diffusion models has opened the door of generative AI,
enabling the translation of textual descriptions into visually compelling images with …

Application of the Modular Bayesian Approach for Inverse Uncertainty Quantification in Nuclear Thermal-Hydraulics Systems

C Wang - arXiv preprint arXiv:2404.04774, 2024 - arxiv.org
In the framework of BEPU (Best Estimate plus Uncertainty) methodology, the uncertainties
involved in the simulations must be quantified to prove that the investigated design is …