37 citations · 37 across the 8 of their papers we have counts for
11 papers · 1 filter
Semantic Steering for Controllable Generation: Tuning-Free Concept Erasure in Multimodal Diffusion Transformers
Qiao Li, Xiaomeng Fu, Yuanshu Zhao +3
Multimodal Diffusion Transformers (MM-DiTs) have demonstrated remarkable text-to-image generation performance, surpassing traditional U-Net-based diffusion models. Nevertheless, th…
Erase but Preserve: Controllable Removal of Copyrighted Animation Characters via Optimized Semantic Anchors
Qiao Li, Xiaomeng Fu, Wangjia Yu +4
The exceptional generation capabilities of text-to-image diffusion models have raised copyright concerns, particularly the unauthorized reproduction of animation characters. Existi…
Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption
Xiaomeng Fu, Jia Li, Yiming Hu +5
Autoregressive (AR) streaming models have emerged as a powerful paradigm for long video generation. However, the linearly growing Key-Value (KV) cache poses a significant bottlenec…
Learning to Discover Forgery Cues for Face Forgery Detection
Jiahe Tian, Peng Chen, Cai Yu +4
Locating manipulation maps, i.e., pixel-level annotation of forgery cues, is crucial for providing interpretable detection results in face forgery detection. Related learning objec…
Unveiling Structural Memorization: Structural Membership Inference Attack for Text-to-Image Diffusion Models
Qiao Li, Xiaomeng Fu, Xi Wang +4
With the rapid advancements of large-scale text-to-image diffusion models, various practical applications have emerged, bringing significant convenience to society. However, model…
Explicit Correlation Learning for Generalizable Cross-Modal Deepfake Detection
Cai Yu, Shan Jia, Xiaomeng Fu +6
With the rising prevalence of deepfakes, there is a growing interest in developing generalizable detection methods for various types of deepfakes. While effective in their specific…
Model Will Tell: Training Membership Inference for Diffusion Models
Xiaomeng Fu, Xi Wang, Qiao Li +3
Diffusion models pose risks of privacy breaches and copyright disputes, primarily stemming from the potential utilization of unauthorized data during the training phase. The Traini…
OSM-Net: One-to-Many One-shot Talking Head Generation with Spontaneous Head Motions
Jin Liu, Xi Wang, Xiaomeng Fu +4
One-shot talking head generation has no explicit head movement reference, thus it is difficult to generate talking heads with head motions. Some existing works only edit the mouth…
MFR-Net: Multi-faceted Responsive Listening Head Generation via Denoising Diffusion Model
Jin Liu, Xi Wang, Xiaomeng Fu +4
Face-to-face communication is a common scenario including roles of speakers and listeners. Most existing research methods focus on producing speaker videos, while the generation of…
FONT: Flow-guided One-shot Talking Head Generation with Natural Head Motions
Jin Liu, Xi Wang, Xiaomeng Fu +4
One-shot talking head generation has received growing attention in recent years, with various creative and practical applications. An ideal natural and vivid generated talking head…
OPT: One-shot Pose-Controllable Talking Head Generation
Jin Liu, Xi Wang, Xiaomeng Fu +4
One-shot talking head generation produces lip-sync talking heads based on arbitrary audio and one source face. To guarantee the naturalness and realness, recent methods propose to…