Neil Nie

I'm the co-founder and CEO of Verne, a robotics startup based in San Francisco.

We're building general-purpose robots for businesses, starting with manufacturers in the United States. We're backed by investors including Y Combinator, Standard Capital, and Crucible Capital.

My research spans robot learning, foundation models, and computer vision. I've worked with Jiajun Wu at Stanford and Shuran Song at Columbia, where I received my B.S. in computer science. At Apple, I worked on computer vision for health and fitness, gaze and gesture, and neural rendering for Apple Vision Pro.

Email Google Scholar X / Twitter

Research

2026 — 2019

STACK robot skills for bookshelf, kitchen, and mug-tree tasks

STACK: Learning Composable Skills by Discovering Spatial and Temporal Structure with Foundation Models

Neil Nie, Wenlong Huang, Jiayuan Mao, Li Fei-Fei, Weiyu Liu, Jiajun Wu

ICRA 2026

Discovering reusable robot skills from a handful of demonstrations, then composing them to handle new scenes, constraints, and longer tasks.

Project Paper Supplement

BLADE robotic manipulation experiments

BLADE: Learning Compositional Behaviors from Demonstration and Language

Weiyu Liu, Neil Nie, Ruohan Zhang, Jiayuan Mao, Jiajun Wu

CoRL 2024 LEAP Workshop oral presentation

Combining imitation learning and planning to turn language-annotated demonstrations into composable robot behaviors.

Structure from Action reconstructs articulated objects through interaction

Structure from Action: Learning Interactions for Articulated Object 3D Structure Discovery

Neil Nie, Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song

IROS 2023

Learning how to interact with unfamiliar objects to discover their parts, reconstruct their geometry, and infer how they move.

Memristor arrays for neural network training

In Situ Training of Feed-Forward and Recurrent Convolutional Memristor Networks

Zhongrui Wang, Can Li, Peng Lin, Mingyi Rao, Yongyang Nie, et al.

Nature Machine Intelligence · 2019

Training convolutional and recurrent neural networks directly in memristor hardware for energy-efficient computing.

Patents

Patent drawing of face and eye motion tracking

Tracking Caloric Expenditure Using a Camera

Aditya Sarathy, James P. Ochs, Yongyang Nie

Apple · US20240041354A1 · Filed 2023

Patent drawing showing golf posture and motion guidance

Posture and Motion Monitoring Using Mobile Devices

Aditya Sarathy, Rene Aguirre Ramos, Umamahesh Srinivas, Yongyang Nie

Apple · US20230096949A1 · Filed 2022

Teaching

Teaching assistant

Stanford University

EE/CS 227 · Robot Perception 2023–2024
CS 224N · Natural Language Processing with Deep Learning 2024
CS 221 · Artificial Intelligence: Principles and Techniques 2023

Columbia University

COMS W4701 · Artificial Intelligence
COMS W4771 · Computational Aspects of Robotics
COMS W3203 · Discrete Mathematics

Service

Reviewer, Conference on Robot Learning (CoRL) · 2025, 2026