6 papers
InfSplign: Inference-Time Spatial Alignment of Text-to-Image Diffusion Models
Sarah Rastegar, Violeta Chatalbasheva, Sieger Falkena +5
Text-to-image (T2I) diffusion models generate high-quality images but often fail to capture the spatial relations specified in text prompts. This limitation can be traced to two fa…
Unified Control for Inference-Time Guidance of Denoising Diffusion Models
Maurya Goyal, Anuj Singh, Hadi Jamali-Rad
Aligning diffusion model outputs with downstream objectives is essential for improving task-specific performance. Broadly, inference-time training-free approaches for aligning diff…
CoDe: Blockwise Control for Denoising Diffusion Models
Anuj Singh, Sayak Mukherjee, Ahmad Beirami +1
Aligning diffusion models to downstream tasks often requires finetuning new models or gradient-based guidance at inference time to enable sampling from the reward-tilted posterior.…
MAGMA: Manifold Regularization for MAEs
Alin Dondera, Anuj Singh, Hadi Jamali-Rad
Masked Autoencoders (MAEs) are an important divide in self-supervised learning (SSL) due to their independence from augmentation techniques for generating positive (and/or negative…
GeNIe: Generative Hard Negative Images Through Diffusion
Soroush Abbasi Koohpayegani, Anuj Singh, K L Navaneet +2
Data augmentation is crucial in training deep models, preventing them from overfitting to limited data. Recent advances in generative AI, e.g., diffusion models, have enabled more…
Federated Learning with Taskonomy for Non-IID Data
Hadi Jamali-Rad, Mohammad Abdizadeh, Anuj Singh
Classical federated learning approaches incur significant performance degradation in the presence of non-IID client data. A possible direction to address this issue is forming clus…