6 papers
Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image Generation
Linfeng Jiang, Steven McDonagh, Yuhang Chen +3
Strong unrestricted adversarial attacks can distort the primary object of an image, hereafter referred to as the subject. To preserve subject integrity without compromising attack…
Beyond Pixel Histories: World Models with Persistent 3D State
Samuel Garcin, Thomas Walker, Steven McDonagh +5
Interactive world models continually generate video by responding to a user's actions, enabling open-ended generation capabilities. However, existing models typically lack a 3D rep…
GaussianHeadTalk: Wobble-Free 3D Talking Heads with Audio Driven Gaussian Splatting
Madhav Agarwal, Mingtian Zhang, Laura Sevilla-Lara +1
Speech-driven talking heads have recently emerged and enable interactive avatars. However, real-world applications are limited, as current methods achieve high visual fidelity but…
Do View-Consistent Representations Matter for Camera-Controlled Video Generation?
Duolikun Danier, Ge Gao, Steven McDonagh +4
Camera-controlled video generation has attracted increasing interest for its applications in simulation, gaming, and world modeling. However, current models often deform rigid obje…
Rethinking Inter-LoRA Orthogonality in Adapter Merging: Insights from Orthogonal Monte Carlo Dropout
Andi Zhang, Xuan Ding, Haofan Wang +2
We propose Orthogonal Monte Carlo Dropout, a mechanism that enforces strict orthogonality when combining sparse semantic vectors without extra time complexity. Low-Rank Adaptation…
Concept-based Adversarial Attack: a Probabilistic Perspective
Andi Zhang, Xuan Ding, Steven McDonagh +1
We propose a concept-based adversarial attack framework that extends beyond single-image perturbations by adopting a probabilistic perspective. Rather than modifying a single image…