Generative Models · Journal of Machine Learning Research 26 (2025) 1 to 54 · 16 min read A research team from the Chinese University of Hong Kong and Florida State University has delivered the first unified convergence theory for a broad class of score based generative models in 2-Wasserstein distance, and it shows that the […]
Wasserstein Convergence Guarantees for Score-Based Generative Models Read More »
ParkDiffusion++: The What-If Prediction Framework That Taught Parking Lots to Reason About Intentions AITrendBlend Machine Learning About Autonomous Driving · arXiv:2602.20923v1 [cs.RO] · 16 min read ParkDiffusion++: The What-If Prediction Framework That Taught Parking Lots to Reason About Intentions How a team from the University of Freiburg and CARIAD SE built a two-stage diffusion system
Preference Score Distillation: Leveraging 2D Rewards to Align Text-to-3D Generation with Human Preference | MedAI Research nn.Module: # Actual implementation would load from HuggingFace or checkpoint return nn.Identity() # Placeholder @torch.no_grad() def forward(self, images: torch.Tensor, prompts: List[str]) -> torch.Tensor: “”” Compute reward scores for images. Args: images: [B, 3, H, W] RGB images in [-1,
RCD: How Three Simple Fixes Are Solving Stable Diffusion’s Biggest Problem | MedAI Research MedAI Research Machine Learning About Deep Learning · TPAMI, 2026 · 16 min read When Stable Diffusion Forgets: How RCD Learned to Remember Every Detail RCD introduces a training-free framework that fixes text-to-image diffusion models’ most frustrating failures — missing objects
RCD: How Three Simple Fixes Are Solving Stable Diffusion’s Biggest Problem Read More »
Knowledge Distillation Medical Image Segmentation • 15 min read Task-Specific KD Segment Anything LoRA ViT-Tiny Diffusion Data Data-Limited Learning Teaching a Tiny Model to Segment Like a Giant Overview. A large vision foundation model is first adapted to one medical task with LoRA, then it teaches a compact student through both its hidden features and
Task-Specific Knowledge Distillation for Medical Image Segmentation Read More »
Introduction: The Challenge of Sparse Cardiac MRI Data Cardiac Magnetic Resonance (CMR) imaging has become an indispensable tool in modern cardiology, providing clinicians with detailed anatomical and functional information about the heart. However, a significant limitation persists in clinical practice: the acquisition of only sparse 2D short-axis slices with substantial inter-slice gaps (typically 8-10mm) rather than complete
The Future of Brain Health is Here — And It’s Powered by AI Imagine a world where doctors can predict how your brain will age — years before symptoms appear. Where Alzheimer’s progression is not a surprise, but a forecast, allowing early, personalized interventions. This isn’t science fiction. It’s the reality being shaped by a
7 Revolutionary Brain Disease Prediction: How AI Beats Disease (But One Flaw Remains) Read More »
Medical imaging has long been the cornerstone of modern diagnostics. From detecting tumors to planning radiotherapy, the quality and availability of imaging modalities like MRI and CT can make or break patient outcomes. But what if one scan could become another? What if a non-invasive MRI could reliably generate a synthetic CT—eliminating radiation exposure and
Introduction: The Future of Glioma Prediction and MRI Generation The medical field has seen a surge in AI-driven diagnostic tools , and one of the most promising advancements is the Treatment-Aware Diffusion Probabilistic Model (TaDiff) . This cutting-edge technology is revolutionizing how we approach diffuse glioma growth prediction and longitudinal MRI generation . In this