A new arXiv paper (2609.36348v1) reports that adding cross-view class-token alignment to diffusion transformer training improves ImageNet linear-probing accuracy by 9.4% with the class token and 10.1%…
Researchers introduced SafeStyle, a training-free framework for calibrated style residual injection in frozen diffusion models that balances style fidelity against content leakage in reference-guided …
Researchers introduced ProgResViT, an input-adaptive Vision Transformer that progressively increases input resolution and model width across rounds, terminating early when predictions are confident. A…
PROVE (Prompt Recovery with Verified Evidence), a training-free, black-box prompt inversion attack introduced in arXiv:2608.13671v1, reconstructs prompts by composing verifiable scene descriptions and…
Meta AI's DINOv2 (2023) scales the original DINO self-supervised vision model into a Vision Foundation Model that matches or beats text-guided models like CLIP on dense pixel-level tasks, introducing …
Researchers from Apple propose FAE (Feature Auto-Encoder), a framework that adapts pre-trained visual encoders like DINO and SigLIP for image generation using as little as a single attention layer. On…
Researchers have identified three core principles—divisibility, transferability, and stability—that govern compositional generalization in AI models, revealing that linear structures in neural represe…
Researchers propose vMFProto, a distributional part-prototype framework that models each class as a mixture of von Mises-Fisher components on the hypersphere for interpretable classification. The meth…