Artificial Intelligence Medical Compendium

Explore the latest research on artificial intelligence and machine learning in medicine.

Showing 21,471 to 21,480 of 216,348 articles

LARGO: Low-Rank Hypernetwork for Handling Missing Modalities

arXiv May 7, 2026
Addressing missing modalities is an important challenge in multimodal image analysis and often relies on complex architectures that do not transfer easily to different datasets without architectural modifications or hyperparameter tuning. While most ... read more 
Computer Vision and Pattern Recognition

Metonymy in vision models undermines attention-based interpretability

arXiv May 7, 2026
Part-based reasoning is a classical strategy to make a computer vision model directly focus on the object parts that are relevant to the downstream task. In the context of deep learning, this also serves to improve by-design interpretability, often b... read more 
Computer Vision and Pattern Recognition

Uncovering Entity Identity Confusion in Multimodal Knowledge Editing

arXiv May 7, 2026
Multimodal knowledge editing (MKE) aims to correct the internal knowledge of large vision-language models after deployment, yet the behavioral patterns of post-edit models remain underexplored. In this paper, we identify a systemic failure mode in ed... read more 
Computation and Language cs.CV

Dynamic Pondering Sparsity-aware Mixture-of-Experts Transformer for Event Stream based Visual Object Tracking

arXiv May 7, 2026
Despite significant progress, RGB-based trackers remain vulnerable to challenging imaging conditions, such as low illumination and fast motion. Event cameras offer a promising alternative by asynchronously capturing pixel-wise brightness changes, pro... read more 
Computer Vision and Pattern Recognition cs.AI

Continuous Expert Assembly: Instance-Conditioned Low-Rank Residuals for All-in-One Image Restoration

arXiv May 7, 2026
Real-world image degradation is often unknown, spatially non-uniform, and compositional, requiring all-in-one restoration models to adapt a single set of weights to diverse local corruption patterns without test-time degradation labels. Existing meth... read more 
Computer Vision and Pattern Recognition cs.AI

Autoregressive Visual Generation Needs a Prologue

arXiv May 7, 2026
In this work, we propose Prologue, an approach to bridging the reconstruction-generation gap in autoregressive (AR) image generation. Instead of modifying visual tokens to satisfy both reconstruction and generation, Prologue generates a small set of ... read more 
Computer Vision and Pattern Recognition cs.AI cs.LG

SymDrift: One-Shot Generative Modeling under Symmetries

arXiv May 7, 2026
Generative modeling of physical systems, such as molecules, requires learning distributions that are invariant under global symmetries, such as rotations in three-dimensional space. Equivariant diffusion and flow matching models can incorporate such ... read more 
Machine Learning cs.AI

AI-Generated Images: What Humans and Machines See When They Look at the Same Image

arXiv May 7, 2026
The misuse of generative AI in online disinformation campaigns highlights the urgent need for transparent and explainable detection systems. In this work, we investigate how detectors for AI-generated images can be more effective in providing human-u... read more 
Computer Vision and Pattern Recognition cs.AI

Learning Discrete Autoregressive Priors with Wasserstein Gradient Flow

arXiv May 7, 2026
Discrete image tokenizers are commonly trained in two stages: first for reconstruction, and then with a prior model fitted to the frozen token sequences. This decoupling leaves the tokenizer unaware of the model that will later generate its tokens. A... read more 
Computer Vision and Pattern Recognition cs.AI cs.LG

Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles

arXiv May 7, 2026
The rapid emergence of generative image models has led to the development of specialized watermarking techniques, particularly in-generation methods such as seed-based embedding. However, current evaluations in this area remain largely empirical, mak... read more 
Cryptography and Security cs.CV
Popular Topics
Recent Journals