arXiv:2603.22094v2 Announce Type: replace
Abstract: As vision-language models (VLMs) are increasingly deployed in open-world scenarios, they can be easily induced by visual jailbreak attacks to generate harmful content, posing serious risks to model s…
arXiv:2603.24458v1 Announce Type: new
Abstract: While proprietary systems such as Seedance-2.0 have achieved remarkable success in omni-capable video generation, open-source alternatives significantly lag behind. Most academic models remain heavily fr…
arXiv:2603.21387v2 Announce Type: replace
Abstract: Facial expression recognition relies on facial data that inherently expose identity and thus raise significant privacy concerns. Current privacy-preserving methods typically fail in realistic open-se…
arXiv:2603.24454v1 Announce Type: new
Abstract: Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabilities in detecting artifacts across differ…
arXiv:2603.20012v2 Announce Type: replace
Abstract: Current diffusion-based makeup transfer methods commonly use the makeup information encoded by off-the-shelf foundation models (e.g., CLIP) as condition to preserve the makeup style of reference imag…
arXiv:2603.24434v1 Announce Type: new
Abstract: Frailty is a condition in aging medicine characterized by diminished physiological reserve and increased vulnerability to stressors. However, frailty assessment remains subjective, heterogeneous, and dif…
arXiv:2603.18739v2 Announce Type: replace
Abstract: Deploying high-performance dense prediction models on resource-constrained edge devices remains challenging due to strict limits on computation and memory. In practice, lightweight systems for object…
arXiv:2603.24407v1 Announce Type: new
Abstract: Generating realistic 3D hand motion from natural language is vital for VR, robotics, and human-computer interaction. Existing methods either focus on full-body motion, overlooking detailed hand gestures,…
arXiv:2603.18067v2 Announce Type: replace
Abstract: The low-light conditions are challenging to the vision-centric perception systems for autonomous driving in the dark environment. In this paper, we propose a new benchmark dataset (named DarkDriving)…
arXiv:2603.24388v1 Announce Type: new
Abstract: Medical imaging models frequently fail when deployed across hospitals, scanners, populations, or imaging protocols due to domain shift, limiting their clinical reliability. While transfer learning and do…