Mastering text-to-image diffusion: Recaptioning, planning, and generating with multimodal llms
Diffusion models have exhibit exceptional performance in text-to-image generation and
editing. However, existing methods often face challenges when handling complex text …
editing. However, existing methods often face challenges when handling complex text …
Retrieval-augmented generation for ai-generated content: A survey
The development of Artificial Intelligence Generated Content (AIGC) has been facilitated by
advancements in model algorithms, scalable foundation model architectures, and the …
advancements in model algorithms, scalable foundation model architectures, and the …
Structure-Guided Adversarial Training of Diffusion Models
Diffusion models have demonstrated exceptional efficacy in various generative applications.
While existing models focus on minimizing a weighted sum of denoising score matching …
While existing models focus on minimizing a weighted sum of denoising score matching …
Consistency flow matching: Defining straight flows with velocity consistency
Flow matching (FM) is a general framework for defining probability paths via Ordinary
Differential Equations (ODEs) to transform between noise and data samples. Recent …
Differential Equations (ODEs) to transform between noise and data samples. Recent …
Distribution-aware data expansion with diffusion models
The scale and quality of a dataset significantly impact the performance of deep models.
However, acquiring large-scale annotated datasets is both a costly and time-consuming …
However, acquiring large-scale annotated datasets is both a costly and time-consuming …
VideoTetris: Towards Compositional Text-to-Video Generation
Diffusion models have demonstrated great success in text-to-video (T2V) generation.
However, existing methods may face challenges when handling complex (long) video …
However, existing methods may face challenges when handling complex (long) video …
EditWorld: Simulating World Dynamics for Instruction-Following Image Editing
Diffusion models have significantly improved the performance of image editing. Existing
methods realize various approaches to achieve high-quality image editing, including but not …
methods realize various approaches to achieve high-quality image editing, including but not …
Distilling Diffusion Models to Efficient 3D LiDAR Scene Completion
S Zhang, A Zhao, L Yang, Z Li, C Meng, H Xu… - arxiv preprint arxiv …, 2024 - arxiv.org
Diffusion models have been applied to 3D LiDAR scene completion due to their strong
training stability and high completion quality. However, the slow sampling speed limits the …
training stability and high completion quality. However, the slow sampling speed limits the …
TextMatch: Enhancing Image-Text Consistency Through Multimodal Optimization
Text-to-image generative models excel in creating images from text but struggle with
ensuring alignment and consistency between outputs and prompts. This paper introduces …
ensuring alignment and consistency between outputs and prompts. This paper introduces …
Distribution-Aware Data Expansion with Diffusion Models
L Yang, JH Yong, H Yin, J Jiang, M **ao… - The Thirty-eighth Annual … - openreview.net
The scale and quality of a dataset significantly impact the performance of deep models.
However, acquiring large-scale annotated datasets is both a costly and time-consuming …
However, acquiring large-scale annotated datasets is both a costly and time-consuming …