Vision-Language Models (VLMs) excel at multimodal reasoning, yet it remains unclear whether their answers are grounded in visual evidence or driven by learned language and world priors. Counting provides a precise testbed: when visual evidence confli... read more
Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based on Group Relative Policy Optimization (GRPO), have attracted widespread attention and been successful... read more
Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject out-of-distribution (OOD) inputs. We present a learner-agnostic ACC-OOD benchmark that freezes LNL ch... read more
Accurate estimation of plant skeletal structures (e.g., branching structures) from images is essential for smart agriculture and plant science. Unlike human skeletons with fixed topology, plant skeleton estimation presents a unique challenge, i.e., e... read more
Recent healthcare foundation models have achieved strong predictive performance through large scale self supervised learning, yet their latent representations frequently entangle physiologic severity, intervention intensity, observational structure, ... read more
Synthetic data is widely used in healthcare to create datasets that are similar to original data but without the privacy concerns. Generating and evaluating synthetic data across privacy, utility and fairness is crucial for facilitating high quality ... read more
In the field of Blind Image Quality Assessment (BIQA), accurately predicting the perceptual quality of authentically distorted images remains highly challenging due to the diverse and complex distortions present in natural environments. Although exis... read more
Manually annotating accurate 3D hand poses is extremely time-consuming and labor-intensive. Existing self-supervised hand pose estimation methods leverage the discrepancy between input images and rendered outputs, or multi-view consistency constraint... read more
The promise of Rectified Flow rests on producing self-generated couplings whose trajectories are straight, or nearly so. In practice, trajectories generated by the base flow model can bend and intertwine, and the resulting coupling inherits this dist... read more
Deep learning models achieved high accuracy in pneumonia detection from chest X-rays. However, their generalization across clinical domains remains limited due to variations in imaging devices, acquisition protocols, and institutional conditions. Thi... read more
Join thousands of healthcare professionals staying informed about the latest AI breakthroughs in medicine. Get curated insights delivered to your inbox.