6 papers
ORCA: Hunting Compositional Failures in Text-to-Image Diffusion
Arshia Hemmat, Amirhossein Vahidi, Amitis Shidani +4
Text-to-image diffusion models fail predictably on compositional prompts: attributes bind to the wrong objects, spatial relations invert, and multi-object scenes lose count. Recent…
DirMoE: Dirichlet-routed Mixture of Experts
Amirhossein Vahidi, Hesam Asadollahzadeh, Navid Akhavan Attar +4
Mixture-of-Experts (MoE) models have demonstrated exceptional performance in large-scale language models. Existing routers typically rely on non-differentiable Top-+Softmax, lim…
SIGMMA: Hierarchical Graph-Based Multi-Scale Multi-modal Contrastive Alignment of Histopathology Image and Spatial Transcriptome
Dabin Jeong, Amirhossein Vahidi, Ciro Ramírez-Suástegui +11
Recent advances in computational pathology have leveraged vision-language models to learn joint representations of Hematoxylin and Eosin (HE) images with spatial transcriptomic (ST…
3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology
Mohammad Vali Sanian, Arshia Hemmat, Amirhossein Vahidi +9
A scalable and robust 3D tissue transcriptomics profile can enable a holistic understanding of tissue organization and provide deeper insights into human biology and disease. Most…
Probabilistic Self-supervised Learning via Scoring Rules Minimization
Amirhossein Vahidi, Simon Schoßer, Lisa Wimmer +4
In this paper, we propose a novel probabilistic self-supervised learning via Scoring Rule Minimization (ProSMIN), which leverages the power of probabilistic models to enhance repre…
Diversified Ensemble of Independent Sub-Networks for Robust Self-Supervised Representation Learning
Amirhossein Vahidi, Lisa Wimmer, Hüseyin Anil Gündüz +3
Ensembling a neural network is a widely recognized approach to enhance model performance, estimate uncertainty, and improve robustness in deep supervised learning. However, deep en…