Author

Greg Heinrich

Observed name: Heinrich, Greg

Observed institutions: Nvidia (United Kingdom), Nvidia (United States)

OpenAlex ID: A5030133314

AM-RADIO: Agglomerative Vision Foundation Model Reduce All Domains Into One

2024 · Mike Ranzinger, Greg Heinrich, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 58

PDF

FasterViT: Fast Vision Transformers with Hierarchical Attention

2023 · Hatamizadeh, Ali, Heinrich, Greg, et al. · arXiv (Cornell University) · 54

PDF

VILA-M3: Enhancing Vision-Language Models with Medical Expert Knowledge

2025 · Vishwesh Nath, Wenqi Li, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 32

PDF

RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models

2025 · Greg Heinrich, Mike Ranzinger, et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 28

PDF

Small Language Models are the Future of Agentic AI

2025 · Belcak, Peter, Heinrich, Greg, et al. · arXiv (Cornell University) · 18

PDF

MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models

2024 · Gongfan Fang, Hongxu Yin, et al. · neural information processing systems · 17

PDF

Metaoptimization on a Distributed System for Deep Reinforcement Learning

2019 · Greg Heinrich, Iuri Frosio · Workshop on Machine Learning in HPC Environments · 2

PDF

Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence

2026 · NVIDIA, :, et al. · arXiv (Cornell University) · 1