Research · Teaching · Technology

Alberto Muñoz’s
Digital Library

A curated collection of research papers, teaching materials, technical reports and articles spanning robotics, artificial intelligence, computer vision and engineering.

Explore the collection ↓Browse all PDFs ↗
✉ amunoz@tec.mxLinkedIn ↗Google Scholar ↗
Dr. Alberto Muñoz
Alberto Muñoz curriculum vitaeOpen CV ↗
From Video to KnowledgeExplore From Video to Knowledge ↗
AI tools & experiments

From Ideas to Impact

Explore two interactive AI tools for research, science, technology and innovation.

Science–Technology Landscape and Innovaction in Action
47documents online
30+years in research
100+theses supervised
Curated knowledge

Explore the library

Search the complete collection by subject, title or keyword. Each card opens its corresponding public PDF.

47 documentsUpdated 2026
Cover of Desarrollo de Software con IA para Nvidia DGX Spark🧠PDF Document2026
Artificial Intelligence•2026

Desarrollo de Software con IA para Nvidia DGX Spark — Curso Práctico Completo — Teoría y Pseudocódigo

Curso práctico de desarrollo de software con IA optimizado para NVIDIA DGX Spark, con teoría formal, ecuaciones, coding agents y ocho algoritmos en pseudocódigo.

NVIDIA DGX SparkAI Software DevelopmentPseudocódigo
Open PDF↗
Cover of A Full Pipeline for Running OpenClaw on NVIDIA DGX Spark for Autonomous Satellite Traffic Negotiation🛰️PDF Document2026
Autonomous Systems•2026

A Full Pipeline for Running OpenClaw on NVIDIA DGX Spark for Autonomous Satellite Traffic Negotiation

Autonomous decision-making, agentic negotiation and resilient operation in complex environments.

Autonomous Systems
Open PDF↗GitHub↗
Cover of A Local AI Pipeline on DGX Spark WhatsApp → Voice2Text → NemoClaw_OpenClaw → Gemma → Nemotron - April 30th 2026🎙️PDF Document2026
Speech & Audio AI•2026

A Local AI Pipeline on DGX Spark WhatsApp → Voice2Text → NemoClaw_OpenClaw → Gemma → Nemotron - April 30th 2026

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of A Practical Architectural Comparison of NVIDIA Nemotron-3-Nano-Omni-30B-A3B-Reasoning and Google Gemma 4 26B-A4B🧠PDF Document2026
Artificial Intelligence•2026

A Practical Architectural Comparison of NVIDIA Nemotron-3-Nano-Omni-30B-A3B-Reasoning and Google Gemma 4 26B-A4B

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of AutomaticExtractionStaticImagesFromGB10 Grace Blackwell👁️PDF Document2026
Computer Vision•2026

AutomaticExtractionStaticImagesFromGB10 Grace Blackwell

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of Autonomous Satellite Traffic Negotiation_ An Agentic Approach to Orbital Congestion and Environmental Sustainability🛰️PDF Document2026
Autonomous Systems•2026

Autonomous Satellite Traffic Negotiation_ An Agentic Approach to Orbital Congestion and Environmental Sustainability

Autonomous decision-making, agentic negotiation and resilient operation in complex environments.

Autonomous Systems
Open PDF↗GitHub↗
Cover of Clonación de Voz con XTTS Implementación Local en Arquitectura NVIDIA Jetson _ Spark🎙️PDF Document2026
Speech & Audio AI•2026

Clonación de Voz con XTTS Implementación Local en Arquitectura NVIDIA Jetson _ Spark

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of Comparación de Consumo de Tokens🧠PDF Document2026
Artificial Intelligence•2026

Comparación de Consumo de Tokens

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Control por Modelo Predictivo del Péndulo Invertido🤖PDF Document2026
Robotics & Control•2026

Control por Modelo Predictivo del Péndulo Invertido

Robotics and control research focused on modelling, planning, simulation and optimisation.

Robotics & Control
Open PDF↗GitHub↗
Cover of Cuanto cuesta preguntar a una IA🧠PDF Document2026
Artificial Intelligence•2026

Cuanto cuesta preguntar a una IA

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of De la Ontología Descubierta a la Reconstrucción Semántica 3D Navegable - May 2026👁️PDF Document2026
Computer Vision•2026

De la Ontología Descubierta a la Reconstrucción Semántica 3D Navegable - May 2026

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of Decision Support in the AI Era🧠PDF Document2026
Artificial Intelligence•2026

Decision Support in the AI Era

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Desde transmisiones en vivo de YouTube (YouTube Live Streams) hasta el seguimiento persistente de múltiples objetos (Persistent Multi-Object Tracking) sobre NVIDIA Spark👁️PDF Document2026
Computer Vision•2026

Desde transmisiones en vivo de YouTube (YouTube Live Streams) hasta el seguimiento persistente de múltiples objetos (Persistent Multi-Object Tracking) sobre NVIDIA Spark

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of Energy-Aware Velocity Control Under Spatial Floor Disturbances MPC_iLQR (GPU Acceleration) vs. Adaptive PID and Sliding Mode🤖PDF Document2026
Robotics & Control•2026

Energy-Aware Velocity Control Under Spatial Floor Disturbances MPC_iLQR (GPU Acceleration) vs. Adaptive PID and Sliding Mode

Robotics and control research focused on modelling, planning, simulation and optimisation.

Robotics & Control
Open PDF↗GitHub↗
Cover of From Video to Narrative_ A Technical Pipeline for Video-to-Narrative Analysis Case Study_ Silent Film Excerpts from Charles Chaplin - Jan27 2026👁️PDF Document2026
Computer Vision•2026

From Video to Narrative_ A Technical Pipeline for Video-to-Narrative Analysis Case Study_ Silent Film Excerpts from Charles Chaplin - Jan27 2026

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of From Video to Narrative_ A Technical Pipeline for Video-to-Narrative Analysis Case Study_ Silent Film Excerpts from Charles Chaplin Dec 26-2025👁️PDF Document2025
Computer Vision•2025

From Video to Narrative_ A Technical Pipeline for Video-to-Narrative Analysis Case Study_ Silent Film Excerpts from Charles Chaplin Dec 26-2025

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of From Video to Narrative_ A Technical Pipeline for Video-to-Narrative Analysis Case Study_ Silent Film Excerpts from Charles Chaplin Dec27-2025👁️PDF Document2025
Computer Vision•2025

From Video to Narrative_ A Technical Pipeline for Video-to-Narrative Analysis Case Study_ Silent Film Excerpts from Charles Chaplin Dec27-2025

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of GPU-Accelerated Inverse Structural Anastylosis from Block Collapse Dynamics🤖PDF Document2026
Robotics & Control•2026

GPU-Accelerated Inverse Structural Anastylosis from Block Collapse Dynamics

Robotics and control research focused on modelling, planning, simulation and optimisation.

Robotics & Control
Open PDF↗GitHub↗
Cover of Has the AI Infrastructure Bottleneck Shifted from Computing to Remembering_🧠PDF Document2026
Artificial Intelligence•2026

Has the AI Infrastructure Bottleneck Shifted from Computing to Remembering_

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Instalación y validación de Nemotron-3-Nano-Omni en NVIDIA DGX Spark🧠PDF Document2026
Artificial Intelligence•2026

Instalación y validación de Nemotron-3-Nano-Omni en NVIDIA DGX Spark

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Jenga_GPU_Inverse_Anstylosis_alike_from_Block_Dynamics_1784919121🤖PDF Document2026
Robotics & Control•2026

Jenga_GPU_Inverse_Anstylosis_alike_from_Block_Dynamics_1784919121

Robotics and control research focused on modelling, planning, simulation and optimisation.

Robotics & Control
Open PDF↗GitHub↗
Cover of Jupyter Notebook Vision for Action — Imitation Learning desde Video Pipeline completo_ Video → Embeddings → Behavioral Cloning → Política de control👁️PDF Document2026
Computer Vision•2026

Jupyter Notebook Vision for Action — Imitation Learning desde Video Pipeline completo_ Video → Embeddings → Behavioral Cloning → Política de control

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of La economía tokenizada de la inferencia🧠PDF Document2026
Artificial Intelligence•2026

La economía tokenizada de la inferencia

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Live Video from Plaza Garibaldi ́s Processing from YouTube Streams on NVIDIA Spark A Jupyter-Centric Pipeline for GPU-Accelerated Computer Vision👁️PDF Document2026
Computer Vision•2026

Live Video from Plaza Garibaldi ́s Processing from YouTube Streams on NVIDIA Spark A Jupyter-Centric Pipeline for GPU-Accelerated Computer Vision

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of Methodology for a Full-Spectrum Analytics Framework Linking National AI Capacity to University Performance📊PDF Document2026
Data Science•2026

Methodology for a Full-Spectrum Analytics Framework Linking National AI Capacity to University Performance

Data analysis, statistical learning and evaluation methodologies.

Data Science
Open PDF↗GitHub↗
Cover of Migrating a Voice-to-Text-to-Reasoning Pipeline🎙️PDF Document2026
Speech & Audio AI•2026

Migrating a Voice-to-Text-to-Reasoning Pipeline

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of MoGe-2 Dense 3D Reconstruction on NVIDIA DGX Spark👁️PDF Document2026
Computer Vision•2026

MoGe-2 Dense 3D Reconstruction on NVIDIA DGX Spark

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of Monitoreo Remoto y Ligero de la NVIDIA DGX Spark📘PDF Document2026
Technical Reports•2026

Monitoreo Remoto y Ligero de la NVIDIA DGX Spark

Architecture, implementation, validation and practical engineering lessons learned.

Technical Reports
Open PDF↗GitHub↗
Cover of Nemotron-3-Nano-Omni 30B-A3B-Reasoning-BF16 Modelo Multimodal de Razonamiento Avanzado🧠PDF Document2026
Artificial Intelligence•2026

Nemotron-3-Nano-Omni 30B-A3B-Reasoning-BF16 Modelo Multimodal de Razonamiento Avanzado

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Nemotron-3-Nano-Omni 30B-A3B-Reasoning-BF16🧠PDF Document2026
Artificial Intelligence•2026

Nemotron-3-Nano-Omni 30B-A3B-Reasoning-BF16

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Operación y Recuperación del Stack Completo en Spark AI NVIDIA DGX Spark (GB10) – spark-110e📘PDF Document2026
Technical Reports•2026

Operación y Recuperación del Stack Completo en Spark AI NVIDIA DGX Spark (GB10) – spark-110e

Architecture, implementation, validation and practical engineering lessons learned.

Technical Reports
Open PDF↗GitHub↗
Cover of Operational Principles of Semantic 3D Reconstruction from Video👁️PDF Document2026
Computer Vision•2026

Operational Principles of Semantic 3D Reconstruction from Video

Computer vision, video understanding, tracking and semantic 3D reconstruction workflows.

Computer Vision
Open PDF↗GitHub↗
Cover of Pipeline local de IA en DGX Spark WhatsApp → Voice2Text → NemoClaw_OpenClaw → Gemma → Nemotron Abril 30 2026🎙️PDF Document2026
Speech & Audio AI•2026

Pipeline local de IA en DGX Spark WhatsApp → Voice2Text → NemoClaw_OpenClaw → Gemma → Nemotron Abril 30 2026

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of PrimeFrequency Neural Inverse Kinematics versus HaltonPrime ConfigurationSpace Planning from 5 to 30 DOF🤖PDF Document2026
Robotics & Control•2026

PrimeFrequency Neural Inverse Kinematics versus HaltonPrime ConfigurationSpace Planning from 5 to 30 DOF

Robotics and control research focused on modelling, planning, simulation and optimisation.

Robotics & Control
Open PDF↗GitHub↗
Cover of Radio1_Audio a Texto con Aceleración CUDA en GPU NVIDIA SPARK GB10🎙️PDF Document2026
Speech & Audio AI•2026

Radio1_Audio a Texto con Aceleración CUDA en GPU NVIDIA SPARK GB10

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of Radio1_Audio to Text with CUDA Acceleration on GPU NVIDIA SPARK GB10_ Implementation, Results, and Performance Analysis🎙️PDF Document2026
Speech & Audio AI•2026

Radio1_Audio to Text with CUDA Acceleration on GPU NVIDIA SPARK GB10_ Implementation, Results, and Performance Analysis

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of RealTimeVirtualDigitalTwinIofaDriver🤖PDF Document2026
Robotics & Control•2026

RealTimeVirtualDigitalTwinIofaDriver

Robotics and control research focused on modelling, planning, simulation and optimisation.

Robotics & Control
Open PDF↗GitHub↗
Cover of Text-to-Voice en DGX Spark via OpenClaw y Microsoft TTS Incident Report #2🎙️PDF Document2026
Speech & Audio AI•2026

Text-to-Voice en DGX Spark via OpenClaw y Microsoft TTS Incident Report #2

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of Tokens_Image_vs_Text_1780175556🧠PDF Document2026
Artificial Intelligence•2026

Tokens_Image_vs_Text_1780175556

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
Cover of Tortugas Multi-Agente Orquestadas por OpenClaw🛰️PDF Document2026
Autonomous Systems•2026

Tortugas Multi-Agente Orquestadas por OpenClaw

Autonomous decision-making, agentic negotiation and resilient operation in complex environments.

Autonomous Systems
Open PDF↗GitHub↗
Cover of Voice-to-Text on DGX Spark via OpenClaw and Whisper🎙️PDF Document2026
Speech & Audio AI•2026

Voice-to-Text on DGX Spark via OpenClaw and Whisper

Speech, transcription and voice-generation pipelines on accelerated NVIDIA hardware.

Speech & Audio AI
Open PDF↗GitHub↗
Cover of When Agents Fight Back_ Lessons in Skill Development on NemoClaw_OpenClaw - April 2026🧠PDF Document2026
Artificial Intelligence•2026

When Agents Fight Back_ Lessons in Skill Development on NemoClaw_OpenClaw - April 2026

AI models, agents, inference infrastructure and accelerated computing workflows.

Artificial Intelligence
Open PDF↗GitHub↗
About the collection

Knowledge made open, useful and connected.

This library brings together work in robotics, computer vision, artificial intelligence, embedded systems and engineering education.

The collection is intended for students, researchers, educators and practitioners. Original authorship and source attribution should always be preserved.

amunoz@tec.mxLinkedIn ↗Google Scholar ↗Google Drive archive ↗