影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
67.7/100
前 3%
全站排名 #1,951
发表论文10 篇
平均评分
年均产出3.3 篇/年
Michal Drozdzal
研究方向
Image Generation · Active acquisition · Deep Learning · Medical Imaging · Computer Vision · Semantic Segmentation
18
Entropy Rectifying Guidance for Diffusion and Flow Models
NeurIPS 2025Poster
三作19
Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Control
ICLR 2025Spotlight
二作23
Object-centric binding in Contrastive Language-Image Pretraining
NeurIPS 2025Poster
22
Increasing the Utility of Synthetic Images through Chamfer Guidance
NeurIPS 2025Poster
通讯17
Improving the Scaling Laws of Synthetic Data with Deliberate Practice
ICML 2025Oral
23
Boosting Latent Diffusion with Perceptual Objectives
ICLR 2025Poster
27
OC-CLIP : Object-centric binding in Contrastive Language-Image Pretraining
ICLR 2025Rejected