452 citations · 1k across the 29 of their papers we have counts for
34 papers
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
iGRPO: Self-Feedback-Driven LLM Reasoning
Ali Hatamizadeh, Shrimai Prabhumoye, Igor Gitman +5
Large Language Models (LLMs) have shown promise in solving complex mathematical problems, yet they still fall short of producing accurate and consistent solutions. Reinforcement Le…
RLP: Reinforcement as a Pretraining Objective
Ali Hatamizadeh, Syeda Nahida Akter, Shrimai Prabhumoye +5
The dominant paradigm for training large reasoning models starts with pre-training using next-token prediction loss on vast amounts of data. Reinforcement learning, while powerful…
Gated Delta Networks: Improving Mamba2 with Delta Rule
Songlin Yang, Jan Kautz, Ali Hatamizadeh
Linear Transformers have gained attention as efficient alternatives to standard Transformers, but their performance in retrieval and long-context tasks has been limited. To address…
MambaVision: A Hybrid Mamba-Transformer Vision Backbone
Ali Hatamizadeh, Jan Kautz
We propose a novel hybrid Mamba-Transformer backbone, MambaVision, specifically tailored for vision applications. Our core contribution includes redesigning the Mamba formulation t…
An Empirical Study of Mamba-based Language Models
Roger Waleffe, Wonmin Byeon, Duncan Riach +13
Selective state-space models (SSMs) like Mamba overcome some of the shortcomings of Transformers, such as quadratic computational complexity with sequence length and large inferenc…
DiffiT: Diffusion Vision Transformers for Image Generation
Ali Hatamizadeh, Jiaming Song, Guilin Liu +2
Diffusion models with their powerful expressivity and high sample quality have achieved State-Of-The-Art (SOTA) performance in the generative domain. The pioneering Vision Transfor…
ViR: Towards Efficient Vision Retention Backbones
Ali Hatamizadeh, Michael Ranzinger, Shiyi Lan +3
Vision Transformers (ViTs) have attracted a lot of popularity in recent years, due to their exceptional capabilities in modeling long-range spatial dependencies and scalability for…
FasterViT: Fast Vision Transformers with Hierarchical Attention
Ali Hatamizadeh, Greg Heinrich, Hongxu Yin +4
We design a new family of hybrid CNN-ViT neural networks, named FasterViT, with a focus on high image throughput for computer vision (CV) applications. FasterViT combines the benef…
Biomedical image analysis competitions: The state of current participation practice
Matthias Eisenmann, Annika Reinke, Vivienn Weru +352
The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known abou…
MONAI: An open-source framework for deep learning in healthcare
M. Jorge Cardoso, Wenqi Li, Richard Brown +53
Artificial Intelligence (AI) is having a tremendous impact across most areas of science. Applications of AI in healthcare have the potential to improve our ability to detect, diagn…
Split-U-Net: Preventing Data Leakage in Split Learning for Collaborative Multi-Modal Brain Tumor Segmentation
Holger R. Roth, Ali Hatamizadeh, Ziyue Xu +4
Split learning (SL) has been proposed to train deep learning models in a decentralized manner. For decentralized healthcare applications with vertical data partitioning, SL can be…
Global Context Vision Transformers
Ali Hatamizadeh, Hongxu Yin, Greg Heinrich +2
We propose global context vision transformer (GC ViT), a novel architecture that enhances parameter and compute utilization for computer vision. Our method leverages global context…
UNetFormer: A Unified Vision Transformer Model and Pre-Training Framework for 3D Medical Image Segmentation
Ali Hatamizadeh, Ziyue Xu, Dong Yang +3
Vision Transformers (ViT)s have recently become popular due to their outstanding modeling capabilities, in particular for capturing long-range information, and scalability to datas…
RAVIR: A Dataset and Methodology for the Semantic Segmentation and Quantitative Analysis of Retinal Arteries and Veins in Infrared Reflectance Imaging
Ali Hatamizadeh, Hamid Hosseini, Niraj Patel +5
The retinal vasculature provides important clues in the diagnosis and monitoring of systemic diseases including hypertension and diabetes. The microvascular system is of primary in…
GradViT: Gradient Inversion of Vision Transformers
Ali Hatamizadeh, Hongxu Yin, Holger Roth +4
In this work we demonstrate the vulnerability of vision transformers (ViTs) to gradient-based inversion attacks. During this attack, the original data batch is reconstructed given…
Closing the Generalization Gap of Cross-silo Federated Medical Image Segmentation
An Xu, Wenqi Li, Pengfei Guo +7
Cross-silo federated learning (FL) has attracted much attention in medical imaging analysis with deep learning in recent years as it can resolve the critical issues of insufficient…
Auto-FedRL: Federated Hyperparameter Optimization for Multi-institutional Medical Image Segmentation
Pengfei Guo, Dong Yang, Ali Hatamizadeh +14
Federated learning (FL) is a distributed machine learning technique that enables collaborative model training while avoiding explicit data sharing. The inherent privacy-preserving…
HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet
Cheng Peng, Andriy Myronenko, Ali Hatamizadeh +6
Semantic segmentation of 3D medical images is a challenging task due to the high variability of the shape and pattern of objects (such as organs or tumors). Given the recent succes…
QU-BraTS: MICCAI BraTS 2020 Challenge on Quantifying Uncertainty in Brain Tumor Segmentation - Analysis of Ranking Scores and Benchmarking Results
Raghav Mehta, Angelos Filos, Ujjwal Baid +89
Deep learning (DL) models have provided state-of-the-art performance in various medical imaging benchmarking challenges, including the Brain Tumor Segmentation (BraTS) challenges.…
Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis
Yucheng Tang, Dong Yang, Wenqi Li +5
Vision Transformers (ViT)s have shown great performance in self-supervised learning of global and local representations that can be transferred to downstream applications. Inspired…
Improving Pneumonia Localization via Cross-Attention on Medical Images and Reports
Riddhish Bhalodia, Ali Hatamizadeh, Leo Tam +4
Localization and characterization of diseases like pneumonia are primary steps in a clinical pipeline, facilitating detailed clinical diagnosis and subsequent treatment planning. A…
The Power of Proxy Data and Proxy Networks for Hyper-Parameter Optimization in Medical Image Segmentation
Vishwesh Nath, Dong Yang, Ali Hatamizadeh +4
Deep learning models for medical image segmentation are primarily data-driven. Models trained with more data lead to improved performance and generalizability. However, training is…
UNETR: Transformers for 3D Medical Image Segmentation
Ali Hatamizadeh, Yucheng Tang, Vishwesh Nath +5
Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past de…