Physical AI, Robotics, and Intelligent Systems Lab
We build physical intelligent agents that can perceive, reason, and act in the real world, from robot arms and legged robots to humanoids and autonomous vehicles.
Robots that see, think, and act
The PARIS Lab, directed by Prof. Zhiyu Huang, studies how to give robots the intelligence to work in the messy, dynamic real world. Our research sits at the intersection of robotics, machine learning, and embodied AI, with a focus on foundation models, efficient learning, and human-centered intelligence.
We validate our ideas on real hardware, from dual-arm manipulators and quadrupeds to autonomous vehicles.
Embodied & Physical AI
VLA models, world models, and generative AI that unify perception, reasoning, and action.
Robotic Navigation & Manipulation
Foundation-model-based robots that move and manipulate in unstructured environments.
Efficient & Adaptive Learning
Data-efficient fine-tuning, RL, imitation, and human-in-the-loop adaptation.
Robots in action
Mem4Act
Latent memory that lets a dual-arm robot solve long-horizon tasks that depend on what it saw earlier.
TIC-VLA
A latency-aware VLA that lets a quadruped follow language instructions through crowded spaces in real time.
AutoVLA
A vision-language-action model for end-to-end driving with adaptive reasoning and RL fine-tuning.
Latest updates
- Mem4Act, latent memory for long-horizon robotic manipulation, is out on arXiv with a project page.
- Our reasoning-centric dataset and benchmark for long-tail driving, nuReasoning, has been accepted at NeurIPS 2026!
- Prof. Zhiyu Huang joined NC State as an Assistant Professor and launched the PARIS Lab. We are recruiting Ph.D. students for Fall 2027.
- We are organizing the Workshop on Foundation Models for V2X-Based Cooperative Autonomous Driving at CVPR 2026.
We are recruiting Ph.D. students for Fall 2027
Join a new lab from day one: help shape its research agenda, build its robots, and publish at top venues in robotics, machine learning, and computer vision.
