Latest AI and machine learning research in product alert for healthcare professionals.
Background: As required by the 21st Century Cures Act, all test results, including final radiology r...
Clinical vision models are often deployed as frozen black boxes with no access to internals, retrain...
Post-hoc class activation maps (CAMs) are a standard tool for inspecting the evidence behind an imag...
Vision-language-action (VLA) models currently demonstrate strong performance in a wide range of real...
Recent text-to-image generation models have achieved remarkable visual quality, but improving them t...
Microscaling (MX) formats are emerging as a hardware-supported approach to efficient training and in...
Existing synthetic image evaluators typically provide only a scalar quality score and do not identif...
Anticipatory neurophysiological activity before unpredictable emotional events has been reported for...
Vision Language Models (VLMs) are widely deployed in safety-critical scenarios, and understanding to...
Rapid assessment of building damage after natural disasters is essential to support emergency respon...
Machine unlearning has emerged as a critical post-hoc safety measure to erase sensitive concepts fro...
Pixel diffusion models generate RGB images directly, avoiding the bottleneck of an autoencoder, yet ...
To comply with recent regulations requiring traceable generated content, modern watermarking has ado...
Vision-Language-Action (VLA) models for autonomous driving rely heavily on successful expert demonst...
Accurate segmentation of post-treatment brain metastases is essential for treatment planning, longit...
When post-training large language models on tasks with semi-verifiable rewards, there are many facto...
Medical vision-language model (VLM) post-training is commonly evaluated through answer accuracy. We ...
Generative AI systems are increasingly used, but aligning their outputs with user requirements poses...
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing ...
Event cameras provide a high dynamic range and preserve brightness-change cues in lighting condition...
Foundation models are post-trained with reinforcement learning (RL) to maximize specific rewards, su...