collaborators

6 papers

cs.LG2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2026

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…

cs.CV2025

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…