1 citations · 3 across the 14 of their papers we have counts for
16 papers · 1 filter
Breaking the Uniformity Trap: Scaling Video Diffusion Model via SplitMoE
Yu Xu, Yuxin Zhang, Xiao Yang +7
Mixture-of-Experts (MoE), popularized by large language models, is a promising paradigm for scaling visual generative models. However, conventional token-wise MoE routes tokens ind…
Beyond Pixels: Visual Metaphor Transfer via Schema-Driven Agentic Reasoning
Yu Xu, Yuxin Zhang, Lin Gao +3
A visual metaphor constitutes a high-order form of human creativity, employing cross-domain semantic fusion to transform abstract concepts into impactful visual rhetoric. Despite t…
TAG-MoE: Task-Aware Gating for Unified Generative Mixture-of-Experts
Yu Xu, Hongbin Yan, Juan Cao +11
Unified image generation and editing models suffer from severe task interference in dense diffusion transformers architectures, where a shared parameter space must compromise betwe…
HunyuanVideo-HOMA: Generic Human-Object Interaction in Multimodal Driven Human Animation
Ziyao Huang, Zixiang Zhou, Juan Cao +9
To address key limitations in human-object interaction (HOI) video generation -- specifically the reliance on curated motion data, limited generalization to novel objects/scenarios…
In-Context Brush: Zero-shot Customized Subject Insertion with Context-Aware Latent Space Manipulation
Yu Xu, Fan Tang, You Wu +6
Recent advances in diffusion models have enhanced multimodal-guided visual generation, enabling customized subject insertion that seamlessly "brushes" user-specified objects into a…
Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
Haipeng Fang, Sheng Tang, Juan Cao +3
Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the de…
Interactive Visual Assessment for Text-to-Image Generation Models
Xiaoyue Mi, Fan Tang, Juan Cao +5
Visual generation models have achieved remarkable progress in computer graphics applications but still face significant challenges in real-world deployment. Current assessment appr…
HeadRouter: A Training-free Image Editing Framework for MM-DiTs by Adaptively Routing Attention Heads
Yu Xu, Fan Tang, Juan Cao +5
Diffusion Transformers (DiTs) have exhibited robust capabilities in image generation tasks. However, accurate text-guided image editing for multimodal DiTs (MM-DiTs) still poses a…
AnchorCrafter: Animate Cyber-Anchors Selling Your Products via Human-Object Interacting Video Generation
Ziyi Xu, Ziyao Huang, Juan Cao +7
The generation of anchor-style product promotion videos presents promising opportunities in e-commerce, advertising, and consumer engagement. Despite advancements in pose-guided hu…
Visual-Friendly Concept Protection via Selective Adversarial Perturbations
Xiaoyue Mi, Fan Tang, You Wu +3
Personalized concept generation by tuning diffusion models with a few images raises potential legal and ethical concerns regarding privacy and intellectual property rights. Researc…
U-VAP: User-specified Visual Appearance Personalization via Decoupled Self Augmentation
You Wu, Kean Liu, Xiaoyue Mi +3
Concept personalization methods enable large text-to-image models to learn specific subjects (e.g., objects/poses/3D models) and synthesize renditions in new contexts. Given that t…
Make-Your-Anchor: A Diffusion-based 2D Avatar Generation Framework
Ziyao Huang, Fan Tang, Yong Zhang +4
Despite the remarkable process of talking-head-based avatar-creating solutions, directly generating anchor-style videos with full-body motions remains challenging. In this study, w…
Adversarial Robust Memory-Based Continual Learner
Xiaoyue Mi, Fan Tang, Zonghan Yang +4
Despite the remarkable advances that have been made in continual learning, the adversarial vulnerability of such methods has not been fully discussed. We delve into the adversarial…
Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation
Xiaoyue Mi, Fan Tang, Yepeng Weng +5
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural…
Dance Your Latents: Consistent Dance Generation through Spatial-temporal Subspace Attention Guided by Motion Flow
Haipeng Fang, Zhihao Sun, Ziyao Huang +3
The advancement of generative AI has extended to the realm of Human Dance Generation, demonstrating superior generative capacities. However, current methods still exhibit deficienc…
Progressive Open Space Expansion for Open-Set Model Attribution
Tianyun Yang, Danding Wang, Fan Tang +3
Despite the remarkable progress in generative technology, the Janus-faced issues of intellectual property protection and malicious content supervision have arisen. Efforts have bee…