AI4CE Lab

Emergent Outlier View Rejection in Visual Geometry Grounded Transformers

Sat, 17 Jan 2026 00:00:00 +0000

Thinking in 360°: Humanoid Visual Search in the Wild

Sat, 17 Jan 2026 00:00:00 +0000

Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI

Sat, 17 Jan 2026 00:00:00 +0000

Adversarial Exploitation of Data Diversity Improves Visual Localization

Wed, 25 Jun 2025 00:00:00 +0000

Extrapolated Urban View Synthesis Benchmark

Wed, 25 Jun 2025 00:00:00 +0000

GARF: Learning Generalizable 3D Reassembly for Real-World Fractures

Wed, 25 Jun 2025 00:00:00 +0000

Co-VisiON: Co-Visibility ReasONing on Sparse Image Sets of Indoor Scenes

Fri, 20 Jun 2025 00:00:00 +0000

VLM See, Robot Do: Human Demo Video to Robot Action Plan via Vision Language Model

Fri, 28 Feb 2025 00:00:00 +0000

NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments

Fri, 31 Jan 2025 00:00:00 +0000

Self-Supervised Place Recognition by Refining Temporal and Featural Pseudo Labels from Panoramic Data

Wed, 01 Jan 2025 00:00:00 +0000

CityWalker: Learning Embodied Urban Navigation from Web-Scale Videos

Thu, 05 Dec 2024 00:00:00 +0000

Memorize What Matters: Emergent Scene Decomposition from Multitraverse

Wed, 25 Sep 2024 00:00:00 +0000

Multiview Scene Graph

Wed, 25 Sep 2024 00:00:00 +0000

FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstruction

Sun, 15 Sep 2024 00:00:00 +0000

EgoPAT3Dv2: Predicting 3D Action Target from 2D Egocentric Vision for Human-Robot Interaction

Sun, 21 Jul 2024 00:00:00 +0000

Multiagent Multitraversal Multimodal Self-Driving: Open MARS Dataset

Sun, 21 Jul 2024 00:00:00 +0000

ActFormer: Scalable Collaborative Perception via Active Queries

Thu, 18 Jul 2024 00:00:00 +0000

LUWA Dataset: Learning Lithic Use-Wear Analysis on Microscopic Images

Thu, 18 Jul 2024 00:00:00 +0000

NYC-Indoor-VPR: A Long-Term Indoor Visual Place Recognition Dataset with Semi-Automatic Annotation

Thu, 18 Jul 2024 00:00:00 +0000

Tell Me Where You Are: Multimodal LLMs Meet Place Recognition

Thu, 18 Jul 2024 00:00:00 +0000

LiDAR-based 4D Occupancy Completion and Forecasting

Tue, 17 Oct 2023 00:00:00 +0000

Among Us: Adversarially Robust Collaborative Perception by Consensus

Mon, 27 Mar 2023 00:00:00 +0000

SSCBench: A Large-Scale 3D Semantic Scene Completion Benchmark for Autonomous Driving

Mon, 27 Mar 2023 00:00:00 +0000

Collaborative Multi-Object Tracking with Conformal Uncertainty Propagation

Sat, 25 Mar 2023 00:00:00 +0000

Metric-Free Exploration for Topological Mapping by Task and Motion Imitation in Feature Space

Thu, 16 Mar 2023 00:00:00 +0000

Toward Zero-Shot Sim-to-Real Transfer Learning for Pneumatic Soft Robot 3D Proprioceptive Sensing

Wed, 08 Mar 2023 00:00:00 +0000

DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization

Mon, 20 Feb 2023 00:00:00 +0000

VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion

Mon, 20 Feb 2023 00:00:00 +0000

Learning Simultaneous Navigation and Construction in Grid Worlds

Wed, 01 Feb 2023 00:00:00 +0000

Uncertainty Quantification of Collaborative Detection for Self-Driving

Fri, 20 Jan 2023 00:00:00 +0000

Multi-Robot Scene Completion: Towards Task-Agnostic Collaborative Perception

Fri, 02 Sep 2022 00:00:00 +0000

Self-Supervised Visual Place Recognition by Mining Temporal and Feature Neighborhoods

Fri, 19 Aug 2022 00:00:00 +0000

V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous Driving

Thu, 21 Jul 2022 00:00:00 +0000

Self-supervised Spatial Reasoning on Multi-View Line Drawings

Mon, 16 May 2022 00:00:00 +0000

Egocentric Prediction of Action Target in 3D

Thu, 24 Mar 2022 00:00:00 +0000

A Deep Reinforcement Learning Environment for Particle Robot Navigation and Object Manipulation

Sat, 12 Mar 2022 00:00:00 +0000

Deep Weakly Supervised Positioning for Indoor Mobile Robots

Fri, 24 Dec 2021 00:00:00 +0000

Learning Distilled Collaboration Graph for Multi-Agent Perception

Mon, 06 Dec 2021 00:00:00 +0000

NYU-VPR: Long-Term Visual Place Recognition Benchmark with View Direction and Data Anonymization Influences

Sun, 28 Nov 2021 00:00:00 +0000

Mobile 3D Printing Robot Simulation with Viscoelastic Fluids

Fri, 08 Oct 2021 00:00:00 +0000

Mobile projective augmented reality for collaborative robots in construction

Thu, 01 Jul 2021 00:00:00 +0000

Projector-Guided Non-Holonomic Mobile 3D Printing

Wed, 19 May 2021 00:00:00 +0000

Simultaneous Navigation and Construction Benchmarking Environments

Mon, 12 Apr 2021 00:00:00 +0000

Fooling LiDAR Perception via Adversarial Trajectory Perturbation

Mon, 29 Mar 2021 00:00:00 +0000

3D Point Cloud Processing and Learning for Autonomous Driving: Impacting Map Creation, Localization, and Perception

Thu, 24 Dec 2020 00:00:00 +0000

A scene-adaptive descriptor for visual SLAM-based locating applications in built environments

Wed, 01 Apr 2020 00:00:00 +0000

LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood

Wed, 01 Jan 2020 00:00:00 +0000

Real-time Soft Body 3D Proprioception via Deep Vision-based Sensing

Wed, 01 Jan 2020 00:00:00 +0000

Regularizing Neural Networks via Minimizing Hyperspherical Energy

Wed, 01 Jan 2020 00:00:00 +0000

SPARE3D: A Dataset for SPAtial REasoning on Three-View Line Drawings

Wed, 01 Jan 2020 00:00:00 +0000

Deep unsupervised learning of 3D point clouds via graph topology inference and filtering

Wed, 11 Dec 2019 00:00:00 +0000

An assistive low-vision platform that augments spatial cognition through proprioceptive guidance: Point-to-Tell-and-Touch

Sun, 03 Nov 2019 00:00:00 +0000

An Occupancy Grid Mapping enhanced visual SLAM for real-time locating applications in indoor GPS-denied environments

Thu, 01 Aug 2019 00:00:00 +0000

DeepMapping: Unsupervised Map Estimation From Multiple Point Clouds

Thu, 06 Jun 2019 00:00:00 +0000

Primitive Fitting Using Deep Boundary Aware Geometric Segmentation

Wed, 03 Oct 2018 00:00:00 +0000

VLASE: Vehicle Localization by Aggregating Semantic Edges

Mon, 01 Oct 2018 00:00:00 +0000

Simultaneous Edge Alignment and Learning

Mon, 06 Aug 2018 00:00:00 +0000

Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling

Fri, 01 Jun 2018 00:00:00 +0000

FoldingNet: Point cloud auto-encoder via deep grid deformation

Mon, 01 Jan 2018 00:00:00 +0000

Fast Resampling of Three-Dimensional Point Clouds via Graphs

Wed, 01 Nov 2017 00:00:00 +0000

FasTFit: A fast T-spline fitting algorithm

Wed, 01 Nov 2017 00:00:00 +0000

Direct Multichannel Tracking

Sun, 01 Oct 2017 00:00:00 +0000

CASENet: Deep Category-Aware Semantic Edge Detection

Thu, 01 Jun 2017 00:00:00 +0000

Deep Active Learning for Civil Infrastructure Defect Detection and Classification

Mon, 01 May 2017 00:00:00 +0000

Camera marker networks for articulated machine pose estimation

Fri, 01 Jan 2016 00:00:00 +0000

Fast plane extraction in organized point clouds using agglomerative hierarchical clustering

Tue, 01 Jul 2014 00:00:00 +0000

Point-plane SLAM for hand-held 3D sensors

Tue, 01 Jan 2013 00:00:00 +0000

Mon, 01 Jan 0001 00:00:00 +0000

Lab Resources

Mon, 01 Jan 0001 00:00:00 +0000

Our lab has several multi-gpu workstations, tabletop and mobile robots, advanced sensors and 3D printers to cover a wide range of research projects centered around robots and spatial intelligence. Our resources support research interest in Robot Perception, Robot Manipulation, Computer Vision, Autonomous Driving, Scene Representation, Mapping and etc.
Please contact our lab management team for details:

Below is an incomplete overview of the lab and resources:

The Lab - NYU Center For Robotics and Embodied Intelligence

Robots

Sensors

3D printer

Life

Mon, 01 Jan 0001 00:00:00 +0000

Openings

Mon, 01 Jan 0001 00:00:00 +0000

In general, if you are interested in the research in AI4CE, please:

Read the group’s webpage to get a basic sense of the research projects, through our past and recent publications.
Fill this form (instead of emailing the PI directly): https://forms.gle/m4riWUGf6Rd9bTWp8
Wait for our Senior Members’ email reply, but please expect some delay in response due to our busy research schedule. You can also reach out to our Senior Members directly if you are looking for faster responses.
If you want to apply for an international visiting student, please note that we expect your physical visit to last for 6 months ideally (at least for 3 months). Note that NYU needs 2 to 3 months to process all the paperwork for you to apply for VISA, if you need one.

For PostDoc Applicants

Unfortunately, we don’t have fundings to support postdoc researchers for now.

For PhD Applicants

The PI typically advises PhD students from different units of NYU (e.g., CUE/MAE/CSE/Courant), as long as there is a good match of research interests (broadly, AI & Robotics) from a competitive candidate.
Strong coding and/or hands-on robotic skills are basic requirements. Past research publications in relevant fields that overlap with the group’s publication venues (CVPR/NeurIPS/ICRA/AutCon/etc.) are strongly preferred.

For MS & UG & K12

If you are with NYU already, after you have been with AI4CE for at least one semester, paid position might be available in form of lab manager, graders, and/or research assistant. In addition, other ways of engaging with the group officially include taking an independent/guided research course, or MS/capstone project with the PI (we have done that for students from CUE/CSE/MAE/ECE/Courant in the past).
If you are NOT with NYU, we welcome all kinds of volunteering-based research internship (including summer or remote ones), but we cannot offer any paid positions due to the university policy.
Attending our weekly group meeting is the best way to understand what we are doing and to learn about new research opportunities.
If you want to officially register independent study, MS project, or thesis with our lab, please follow the Research Project Guidelines and Proposal Template (open to NYU students).

People

Mon, 01 Jan 0001 00:00:00 +0000