Sitemap

A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.

Posts

blog

NVIDIA RTX A6000 Ada Generation — 48GB GPU for AI, Rendering, and Beyond

Published: June 17, 2023

An in-depth review of the NVIDIA RTX A6000 Ada Generation, a professional GPU with 48GB of VRAM that excels across AI training and inference, professional rendering, and high-performance computing workloads.

How AI Runs on Your GPU — Stable Diffusion, LLMs, Blender, and More

Published: January 22, 2024

A practical walkthrough of how GPU-accelerated AI works under the hood — covering popular tools like Stable Diffusion, LM Studio, Blender, and DaVinci Resolve to demonstrate real-world GPU utilization for AI and creative workloads.

NVIDIA Blackwell at GTC 2024 — The Next Era of GPU Computing

Published: April 01, 2024

My experience at NVIDIA GTC 2024 in San José, covering the unveiling of the NVIDIA Blackwell architecture — a generational leap in GPU computing for AI training, inference, and scientific simulation.

portfolio

Portfolio item number 2

Short description of portfolio item number 2

projects

NeRF on NVIDIA Jetson — Neural Radiance Fields at the Edge

Published: October 22, 2024

Implemented and optimized NeRF (Neural Radiance Fields) on NVIDIA Jetson devices at the Jetson AI Lab, enabling real-time 3D reconstruction from 2D images on edge hardware.

decord2 — Efficient Video Loader for Deep Learning

Published: June 01, 2025

decord2 is a modernized, efficient video loader for deep learning with smart shuffling — a maintained evolution of the deprecated decord library.

Jetson Containers — 30+ AI Libraries Ported to Edge

Published: August 01, 2025

Core contributor to dusty-nv/jetson-containers — the official collection of Machine Learning containers for NVIDIA Jetson and JetPack-L4T.

edge2cloud — ML Containers for NVIDIA CUDA SBSA

Published: January 01, 2026

edge2cloud is a collection of Machine Learning containers for NVIDIA CUDA SBSA (Server Base System Architecture) spanning Jetson, DGX Spark, and cloud deployments.

Deploying Open Source Vision Language Models (VLM) on Jetson — Cosmos Reason 2B

Published: February 24, 2026

Co-author of the official Hugging Face tutorial on deploying NVIDIA Cosmos Reason 2B — a Vision-Language Model with chain-of-thought reasoning — across the entire NVIDIA Jetson family (AGX Thor, AGX Orin, Orin Super Nano) using vLLM.

NemoClaw & OpenShell on Jetson — Edge Manipulation and Functional Behavior

Published: March 01, 2026

Enabled NemoClaw and OpenShell to run on Jetson AGX Orin and Orin Super Nano, bringing NVIDIA’s manipulation and functional behavior models to edge robotics platforms.

Jetson SBSA PyTorch Wheels — CUDA 13.2 for Jetson Orin Family

Published: March 15, 2026

Pioneered the build and validation of public CUDA 13.2 PyTorch wheels for the entire Jetson Orin family using the SBSA (Server Base System Architecture) path — ahead of the official JetPack 7.2 release expected in Q2 2026.

reBot-devArm — Open-Source Robot Arm for Education and Research

Published: March 20, 2026

Contributing to reBot-devArm from Seeed Studio — an open-source robot arm platform designed for students, developers, and researchers.

DGX Spark + Jetson Thor Custom Mini Rack — Compact AI Infrastructure

Published: April 01, 2026

Custom-designed compact AI infrastructure combining 2x NVIDIA DGX Spark, 2x NVIDIA Jetson Thor, and a QNAP QSW-M7308R-4 optical switch — concentrating real AI compute power in the smallest possible footprint.

The Full Stack of Physical AI — CVPR 2026 Tutorial

Published: June 01, 2026

Co-organizer of “The Full Stack of Physical AI: Simulation, Foundation Models, and Edge Deployment for Next-Generation Robotics Applications” — a half-day tutorial at CVPR 2026 in Denver, Colorado.

publications

Didn’t see that coming: a survey on non-verbal social human behavior forecasting

Published in Understanding Social Behavior in Dyadic and Small Group Interactions, 2022

This survey defines the behavior forecasting problem for interactive agents, aiming to unify social signals prediction and human motion forecasting fields.

Recommended citation: German Barquero, Johnny Núnez, Sergio Escalera, Zhen Xu, Wei-Wei Tu, Isabelle Guyon, Cristina Palmero. (2022). "Didn’t see that coming: a survey on non-verbal social human behavior forecasting." Understanding Social Behavior in Dyadic and Small Group Interactions. 139-178.
Download Paper | Download Slides

Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios: Supplementary Material

Published in , 2022

This supplementary material compares spatio-temporal models for human motion and pose forecasting in face-to-face interaction scenarios.

Recommended citation: German Barquero, Johnny Núnez, Zhen Xu, Sergio Escalera, Wei-Wei Tu, Isabelle Guyon, Cristina Palmero. (2022). "Comparison of Spatio-Temporal Models for Human Motion and Pose Forecasting in Face-to-Face Interaction Scenarios: Supplementary Material."
Download Paper | Download Slides

Chalearn LAP challenges on self-reported personality recognition and non-verbal behavior forecasting during social dyadic interactions: Dataset, design, and results

Published in Understanding Social Behavior in Dyadic and Small Group Interactions, 2022

This paper summarizes the 2021 ChaLearn Looking at People Challenge on Understanding Social Behavior in Dyadic and Small Group Interactions, covering two tracks: self-reported personality recognition and behavior forecasting.

Recommended citation: Cristina Palmero, German Barquero, Julio CS Jacques Junior, Albert Clapés, Johnny Núnez, David Curto, Sorina Smeureanu, Javier Selva, Zejian Zhang, David Saeteros, David Gallardo-Pujol, Georgina Guilera, David Leiva, Feng Han, Xiaoxue Feng, Jennifer He, Wei-Wei Tu, Thomas B Moeslund, Isabelle Guyon, Sergio Escalera. (2022). "Chalearn LAP challenges on self-reported personality recognition and non-verbal behavior forecasting during social dyadic interactions: Dataset, design, and results." Understanding Social Behavior in Dyadic and Small Group Interactions. 4-52.
Download Paper | Download Slides

Comparison of Spatio-Temporal Hand Pose Denoising Models

Published in Universitat de Barcelona, 2022

Master thesis comparing spatio-temporal models for hand pose denoising in video sequences, addressing noise in real-world human pose estimation.

Recommended citation: Johnny Núñez. (2022). "Comparison of Spatio-Temporal Hand Pose Denoising Models." Universitat de Barcelona.
Download Paper | Download Slides

Identifying Loitering Behavior with Trajectory Analysis

Published in Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025

Introduced a standardized definition of loitering and a new annotated dataset for trajectory-based loitering detection in thermal surveillance.

Recommended citation: Johnny Núñez, Zenjie Li, Sergio Escalera, Kamal Nasrollahi. (2024). "Identifying Loitering Behavior with Trajectory Analysis." Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 251-259.
Download Paper | Download Slides

Enhancing Clinical Psychology Practice through Data-Driven Machine Learning Monitoring Systems

Published in Cited Here, 2025

This work explores how data-driven machine learning monitoring systems can enhance clinical psychology practice, bridging AI and mental health.

Recommended citation: G. Martínez, A. Trujillo, J. Núñez, J.C.S. Jacques, A. Clapés, et al. (2025). "Enhancing clinical psychology practice through data-driven machine learning monitoring systems."
Download Paper | Download Slides

The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries

Published in arXiv preprint, 2025

FKL provides a C++ API for developing highly-efficient fused GPU kernels, enabling significant performance improvements in GPU-accelerated computing.

Recommended citation: O. Amoros, A. Andaluz, J. Nunez, A.J. Pena. (2025). "The Fused Kernel Library: A C++ API to Develop Highly-Efficient GPU Libraries." arXiv preprint arXiv:2508.07071.
Download Paper | Download Slides

talks

MWC Barcelona 2024 — AI and Edge Computing

Published: February 26, 2024

Attended Mobile World Congress (MWC) 2024 in Barcelona, exploring the latest developments in AI, edge computing, 5G-enabled robotics, and the convergence of telecommunications and Physical AI.

NVIDIA GTC 2024 — AI and Robotics on Edge Devices

Published: March 18, 2024

Attended NVIDIA GTC 2024 in San José as a community member and content creator, covering the unveiling of the NVIDIA Blackwell architecture, advances in Physical AI, and the Jetson ecosystem. Created video content documenting the event, the technology announcements, and hands-on experiences with cutting-edge hardware.

CES 2025 — NVIDIA Cosmos on Jetson Demo

Published: January 07, 2025

Showcased the NVIDIA Cosmos platform running on Jetson AGX Orin at CES 2025. Demonstrated real-time generative world foundation models at the edge, enabling physics-based synthetic data generation and domain-specific model fine-tuning on compact hardware.

ROSCon Spain 2025 — ROS 2 and NVIDIA Robotics

Published: October 01, 2025

Supported NVIDIA’s demo presence at ROSCon Spain 2025 in Barcelona. Connected with the ROS 2 developer community, showcasing NVIDIA Isaac ROS, Jetson-based robotics workflows, and the integration of foundation models with ROS 2 for autonomous systems.

Smart City Expo World Congress 2025 — AI for Urban Robotics

Published: November 01, 2025

Connected with industry experts at the Smart City Expo World Congress 2025 in Barcelona, exploring the role of AI-powered robotics and edge computing in smart city infrastructure, autonomous systems, and urban digital twins.

NeurIPS 2025 — Physical AI Hardware-in-the-Loop Demo

Published: December 08, 2025

Delivered a hardware-in-the-loop Physical AI demo at NeurIPS 2025, showcasing real-time robotic inference with DGX Spark and Jetson Thor connected via optical networking. Demonstrated the end-to-end pipeline from simulation to edge deployment with the NVIDIA Physical AI stack.

Humanoid Forum Zurich — Connect with Experts Workshop

Published: February 20, 2026

Participated in the Humanoid Forum in Zurich, connecting with researchers and industry leaders on humanoid robotics training. Showcased DGX Spark running Isaac Sim for humanoid robot simulation and policy development.

MWC Barcelona 2026 — Physical AI and Edge Robotics

Published: March 01, 2026

Represented NVIDIA at Mobile World Congress 2026 in Barcelona, engaging with the telecom and technology industry on the convergence of Physical AI, 5G-enabled robotics, and edge computing. Demonstrated NVIDIA’s Physical AI stack and connected with industry partners exploring distributed AI and robotic fleet management.

NVIDIA GTC 2026 — Physical AI, GR00T N2, and Jetson Thor

Published: March 17, 2026

Participated in NVIDIA GTC 2026 as an NVIDIA Developer Advocate, engaging with the community around the major Physical AI announcements including:

CVPR 2026 Tutorial — The Full Stack of Physical AI

Published: June 03, 2026

Co-organizer of “The Full Stack of Physical AI: Simulation, Foundation Models, and Edge Deployment for Next-Generation Robotics Applications” — a half-day tutorial at CVPR 2026.

Johnny Núñez Cano