6 papers
When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks
Berk Tinaz, Changzhi Xie, Mahdi Soltanolkotabi
In this paper, we study the gradient descent dynamics for jointly training both layers of a one-hidden-layer ReLU network to fit a linear target function. Concretely, we consider a…
MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI
Paula Arguello, Berk Tinaz, Mohammad Shahab Sepehri +2
Deep learning underpins a wide range of applications in MRI, including reconstruction, artifact removal, and segmentation. However, progress has been driven largely by public datas…
ATHENA: Adaptive Test-Time Steering for Improving Count Fidelity in Diffusion Models
Mohammad Shahab Sepehri, Asal Mehradfar, Berk Tinaz +2
Text-to-image diffusion models achieve high visual fidelity but surprisingly exhibit systematic failures in numerical control when prompts specify explicit object counts. To addres…
Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs
Mohammad Shahab Sepehri, Berk Tinaz, Zalan Fabian +1
Mental visualization, the ability to construct and manipulate visual representations internally, is a core component of human cognition and plays a vital role in tasks involving re…
Emergence and Evolution of Interpretable Concepts in Diffusion Models
Berk Tinaz, Zalan Fabian, Mahdi Soltanolkotabi
Diffusion models have become the go-to method for text-to-image generation, producing high-quality images from pure noise. However, the inner workings of diffusion models is still…
ConceptMix++: Leveling the Playing Field in Text-to-Image Benchmarking via Iterative Prompt Optimization
Haosheng Gan, Berk Tinaz, Mohammad Shahab Sepehri +2
Current text-to-image (T2I) benchmarks evaluate models on rigid prompts, potentially underestimating true generative capabilities due to prompt sensitivity and creating biases that…