Skip to content
conftrace_

Berk Tinaz

4 papers · 2022–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓
🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze

Venues

ICML (2) COLT (1) NeurIPS (1)

Top co-authors

Mahdi Soltanolkotabi (4) Zalan Fabian (3) Changzhi Xie (1)

Research topics

Deep Learning (4) Computer Vision (3) Processing (3) Machine Learning (2) Architectures (2) Models (2) Application Areas (1) Domain-Specific (1) Optimization & Theory · Deep Learning (1) Optimization & Theory · Machine Learning (1)

Keywords

inverse problem (2) sample complexity (1) denoising (1) deep learning (1) gradient descent (1) optimization landscape (1) autoencoders (1) diffusion model (1) convolutional neural network (1) training dynamics (1) latent diffusion model (1) transformer block (1) relu network (1) saddle point (1) multi-scale feature extraction (1) ill-posed inverse problem (1) mri reconstruction (1) data consistency (1) accelerated mri reconstruction (1) hybrid unrolled architecture (1)

Papers

When Both Layers Learn: Training Dynamics of Representing Linear Models via ReLU Networks COLT 2026 Adapt and Diffuse: Sample-adaptive Reconstruction via Latent Diffusion Models ICML 2024 DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency ICML 2024 HUMUS-Net: Hybrid Unrolled Multi-scale Network Architecture for Accelerated MRI Reconstruction NeurIPS 2022