Latest AI and machine learning research in rheumatoid arthritis for healthcare professionals.
The rise of customized diffusion models has fueled a boom in personalized visual content creation, but it also introduces serious risks of malicious misuse, thereby posing threats to personal privacy. Image aesthetics are strongly correlated with human perception of image quality. Motivated by this observation, we address facial privacy protection from a novel aesthetic perspective by degrading th...
Recent advances in Image-to-Video generation allow a single image to be animated into a convincing video under text guidance, raising serious copyright and privacy risks. We propose Anti-Prompt, an image protection approach that injects imperceptible perturbations into an image, inducing visible inconsistencies and structural failures in text-guided I2V generation. Our method is motivated by a sim...
Aging is caused, fully in large part, by the progressive accumulation of damage, yet quantifying age-related damage across tissues and conditions rema...
Despite their remarkable performance, Vision Language Models (VLMs) incur substantial computational overhead due to the large number of visual tokens....
Five years after the discovery of persistent anti-Muslim bias in large language models, most evaluations remain confined to single-turn prompt complet...
Drug repurposing, the application of approved or shelved compounds to new therapeutic indications, offers a cost- and time-efficient alternative to de...
Model fingerprinting, embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect...
Text-conditioned 3D generation has progressed rapidly for images and isolated objects, but producing a hand-object mesh remains challenging: the outpu...
Document image binarization aims to separate foreground text from degraded backgrounds while preserving thin, broken, and low-contrast strokes. Althou...
Liver sinusoidal endothelial cells (LSECs) are increasingly recognized as a critical yet underexplored cell type in anti-fibrotic drug development. Th...
Drug repurposing offers a cost-effective strategy to accelerate therapeutic discovery, but most computational approaches fail to model noncoding genet...
We present EDDY (Exact-marginal Diversification via Divergence-free dYnamics), a guidance mechanism for diffusion and flow matching models that promot...
The rapid growth of molecular foundation models and general-purpose large language models has encouraged a scale-centric view of artificial intelligen...
Metabolic dysfunction is increasingly recognized as a risk factor for poor outcomes in breast cancer, but whether incretin-based therapies confer surv...
Multimodal learning has the potential to improve clinical prediction by integrating complementary data sources, but the incremental value of imaging b...
Anti-doping programs rely on biological testing to detect performance-enhancing drugs, but such testing costs over $800 per sample and is limited by s...
The rapid progress of subject-driven text-to-image synthesis, and in particular DreamBooth, has enabled a consent-free deepfake pipeline: an adversary...
Face Anti-Spoofing (FAS) algorithms, designed to secure face recognition systems against spoofing, struggle with limited dataset diversity, impairing ...
Thermal imaging is crucial for night vision but fundamentally hampered by the ghosting effect, a loss of detailed texture in cluttered photon streams....
Accurate drug response prediction is a critical bottleneck in computational biochemistry, limited by the challenge of modelling the interplay between ...