Related papers: IterComp: Iterative Composition-Aware Feedback Lea…

Large text-guided diffusion models, such as DALLE-2, are able to generate stunning photorealistic images given natural language descriptions. While such models are highly flexible, they struggle to understand the composition of certain…

Diffusion models have significantly improved the quality and diversity of audio generation but are hindered by slow inference speed. Rectified flow enhances inference speed by learning straight-line ordinary differential equation (ODE)…

The field of AI-assisted music creation has made significant strides, yet existing systems often struggle to meet the demands of iterative and nuanced music production. These challenges include providing sufficient control over the…

Diffusion models, particularly latent diffusion models, have demonstrated remarkable success in text-driven human motion generation. However, it remains challenging for latent diffusion models to effectively compose multiple semantic…

Generative models have achieved impressive fidelity in text-to-image synthesis, yet struggle with complex compositional prompts involving multiple constraints. We introduce \textbf{M3 (Multi-Modal, Multi-Agent, Multi-Round)}, a…

We present EARCP (Ensemble Auto-R\'egul\'e par Coh\'erence et Performance), a novel ensemble architecture that dynamically weights heterogeneous expert models based on both their individual performance and inter-model coherence. Unlike…

Diffusion probabilistic models have achieved enormous success in the field of image generation and manipulation. In this paper, we explore a novel paradigm of using the diffusion model and classifier guidance in the latent semantic space…

Recently, the multimedia community has witnessed the rise of diffusion models trained on large-scale multi-modal data for visual content creation, particularly in the field of text-to-image generation. In this paper, we propose a new task…

While recent advancements in generative modeling have significantly improved text-image alignment, some residual misalignment between text and image representations still remains. Some approaches address this issue by fine-tuning models in…

With the rapid development of diffusion models, text-to-image(T2I) models have made significant progress, showcasing impressive abilities in prompt following and image generation. Recently launched models such as FLUX.1 and Ideogram2.0,…

While text-to-visual models now produce photo-realistic images and videos, they struggle with compositional text prompts involving attributes, relationships, and higher-order reasoning such as logic and comparison. In this work, we conduct…

Generating long-term, coherent, and realistic music-conditioned dance sequences remains a challenging task in human motion synthesis. Existing approaches exhibit critical limitations: motion graph methods rely on fixed template libraries,…

Advanced diffusion models have made notable progress in text-to-image compositional generation. However, it is still a challenge for existing models to achieve text-image alignment when confronted with complex text prompts. In this work, we…

Text-to-image diffusion models exhibit remarkable generative capabilities, but lack precise control over object counts and spatial arrangements. This work introduces a two-stage system to address these compositional limitations. The first…

Large-scale text-to-image diffusion models have achieved great success in synthesizing high-quality and diverse images given target text prompts. Despite the revolutionary image generation ability, current state-of-the-art models still…

Recent advances in text-to-image (T2I) diffusion models have enabled remarkable control over various attributes, yet precise color specification remains a fundamental challenge. Existing approaches, such as ColorPeel, rely on model…

Current mainstream methods of aligning diffusion models with human preferences typically employ VLM-based reward models. However, these reward models, pre-trained for semantic alignment, struggle to capture the essential perceptual…

Existing generative models, such as diffusion and auto-regressive networks, are inherently static, relying on a fixed set of pretrained parameters to handle all inputs. In contrast, humans flexibly adapt their internal generative…

Diffusion models have demonstrated remarkable capabilities in generating high-quality samples and enhancing performance across diverse domains through Classifier-Free Guidance (CFG). However, the quality of generated samples is highly…

Text-to-image (T2I) generative models have recently emerged as a powerful tool, enabling the creation of photo-realistic images and giving rise to a multitude of applications. However, the effective integration of T2I models into…