Sensing & Reasoning Lab · Rutgers University
Jorge Ortiz

Jorge Ortiz

Site Director & PI, CRAIG (NSF)
Lead Site PI, CS3 (NSF)
Associate Professor, Rutgers Director, Sensing & Reasoning Lab Research Analyst, New York Yankees

Causal representation learning, multimodal alignment, agentic decision systems.

About

Jorge Ortiz serves as Site Director and Principal Investigator for CRAIG, the NSF Center on Responsible AI & Governance, and Lead Site PI for the NSF Center for Smart Streetscapes (CS3). He directs the Sensing & Reasoning Lab at Rutgers University.

His group builds causal world models and agentic multimodal systems that integrate sensing, inference, and intervention for decision-making at scale across urban systems, sports analytics, and AI governance. The approach separates perception from reasoning. Multimodal encoders learn compact state representations from video, audio, IMU, and network data, while causal reasoning modules plan interventions and generate explanations.

Perception–Reasoning Architecture

Perception

Extract state from
sensor streams

Reasoning

Form hypotheses • plan interventions
adapt to conditions

state flow

Previously, I was at IBM Research and several startups applying machine learning to sensor-driven systems. I received my PhD in Computer Science from UC Berkeley and my BS from MIT.

⚾ Currently: I also serve as Research Analyst for the New York Yankees, applying advanced analytics and computer vision to baseball operations.

Centers & Flagship Initiatives

NSF CENTER

CRAIG — Responsible AI & Governance

Role: Site Director & PI (Rutgers)

Causal inference, accountability, and evaluation pipelines for trustworthy AI in public and enterprise deployments.

NSF CENTER

CS3 — Smart Streetscapes

Role: Lead Site PI (Rutgers)

City-scale sensing and digital twins; causal reasoning for pedestrian safety and closed-loop actuation.

RESEARCH LAB

Sensing & Reasoning Lab

Role: Director

Agentic causal world models; multimodal perception→reasoning stack; interventional analysis and counterfactual simulation.

SPORTS ANALYTICS

New York Yankees

Role: Research Analyst

Biomechanics and strategy models from broadcast + sensor data; embeddings for outcomes; counterfactual search.

Selected Publications

Full list on Google Scholar.

News

2025
Appointed Site Director & PI for CRAIG (NSF Center on Responsible AI & Governance).
2025
Lead Site PI for NSF CS3 (Smart Streetscapes) at Rutgers.
Dec '25
NeurIPS 2025: "DFGauss: Dynamic Focused Masking for Autoregressive 3D Occupancy Prediction" (Sun, Contreras, Ortiz).
Dec '25
NeurIPS Workshops: Two papers accepted - "TellMe Why: Towards Causal Discovery from Urban Video" (UrbanAI) and "PolicyGrid: Acting to Understand, Understanding to Act" (Embodied World Models).

Media & Press

WSJ
WALL STREET JOURNAL

The Overestimation of Artificial Superintelligence

Interviewed about AI capabilities and the hype around superintelligence

Follow-up: Next Steps in Reasoning — My detailed thoughts on the topic
June 13, 2025
NS
NEW SCIENTIST

Robot that learns social cues could feed people with tetraplegia

Coverage of our CoRL 2022 research on socially-aware robot-assisted feeding that uses AI to monitor dining social cues and time food delivery appropriately during group meals.

July 26, 2022

Teaching

ECE 532 — Multimodal Learning for Sensing Systems (Fall 2025)

In-depth exploration of multimodal learning across audio, video, time series, and language/text data, focusing on foundational concepts, advanced techniques, and practical applications for distributed sensing systems.

ECE 252 — Programming Methodology (Spring 2025)

Comprehensive introduction to programming in C and C++ for ECE students, covering foundational concepts through advanced topics including object-oriented programming, modern C++ features, and multithreading.

Contact