ICCV 2025

Meet us at ICCV 2025

Stack AV autonomous truck

Welcome ICCV 2025 Attendees!

Join Stack AV at Booth #230 | Oct 21 - 23, 2025
About Stack
Stack AV is building the future of autonomous freight through cutting-edge robotics, applied AI, and a deep commitment to safety and reliability. We're backed by industry leaders and driven by a mission to solve real-world logistics challenges with breakthrough tech.

Connect with Stack AV at ICCV

Find Us at ICCV 2025

Booth #230
Conference Exhibition Hall
October 21-23, 2025
All conference days
One-on-one meetings available
Reserve your spot with our engineers

Schedule Your Meeting

Want to connect one-on-one at ICCV? Reserve a spot to chat with our engineers, ask questions, and dive deeper into our tech.
Book Your Time Slot

Meet the Minds Behind the Tech

Curious who’s shaping Stack AV’s innovations?
Get to know the engineers attending ICCV and explore the people driving our technology forward.
Alexander Gorban
Staff Software Engineer
Perception team working on Tracking
Shaojun Zhu
Staff Software Engineer
Perception team working on Detection
Jason Ziglar
Director of Software Engineering
Perception Engineering
Ishan Khatri
Senior Software Engineer
Perception team working on Detection
Visesh Chari
Staff Software Engineer
Perception team working on Detection
Dave Langerman
Senior Software Engineer
Perception team working on Detection
Tim Tang
Senior Software Engineer
Localization and Mapping team
Sudipta Sinha
Staff Software Engineer
Perception team working on Calibration

Our Team's Research & Impact

Discover cutting edge work our team is doing, including publications at top tier conferences like ICCV. See how our past and present research is advancing robotics and making real-world impact.

Stack AV in Action

Stack AV Overview GIF

Recent Publications

ContributorConference / JournalYearsorted descendingPaper (Title)
Ishan KhatriCVPR2025Argoverse 2 Challenges 2025 @ Workshop on Autonomous Driving
Ishan KhatriICLR2025Neural Eulerian Scene Flow Fields
Nick DePalmaTHRI2025Scarecrows in Oz: The Use of Large Language Models in HRI
Ishan KhatriECCV2024I Can't Believe It's Not Scene Flow
Ishan KhatriICLR2024ZeroFlow: Scalable Scene Flow via Distillation
Nick DePalmaTHRI2024Face2gesture: Translating facial expressions into robot movements through shared latent space neural networks
Jason ZiglarAutonomous Robots2023Context-aware system synthesis, task assignment, and routing
Jason ZiglarECCV2023Differentiable raycasting for self-supervised occupancy forecasting
Jason ZiglarIROS2023Lidar Panoptic Segmentation and Tracking without Bells and Whistles
Sudipta SinhaCVPR Tutorial2023Privacy-Preserving Visual Localization
Sudipta SinhaRA-L / IROS2023Optimizing Fiducial Marker Placement for Improved Visual Localization
Tim TangAutonomous Robots2023Point-based metric and topological localisation between lidar and overhead imagery
Tim TangRSS2023Self-supervised Lidar place recognition in overhead imagery using unpaired data
Tyler GaraasICRA2023ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation
Sudipta SinhaCVPR2022Learning to Detect Scene Landmarks for Camera Localization
Sudipta SinhaCVPR Workshop2022Towards Storage Efficient and Privacy-Preserving Camera Localization in Pre-Mapped Environments
Visesh ChariCVPR2022Multi-modal 3D Human Pose Estimation with 2D Weak Supervision in Autonomous Driving
Ankit LaddhaCVPR2021Mvfusenet: Improving end-to-end object detection and motion forecasting through multi-view fusion of lidar data
Ankit LaddhaIROS2021Rv-fusenet: Range view based fusion of time-series lidar data for joint 3d object detection and motion forecasting
Ishan KhatriIROS2021Agent Aware State Estimation for Traffic Light Classification in Autnomous Vehicles
Sudipta SinhaCVPR2021PatchMatch-Based Neighborhood Consensus for Semantic Correspondence
Sudipta SinhaCVPR2021Privacy-Preserving Image Features via Adversarial Affine Subspace Embeddings
Sudipta SinhaICCV Tutorial2021Privacy-Preserving Visual Localization
Tim TangInternational Journal of Robotics Research2021Self-supervised learning for using overhead imagery as maps in outdoor range sensor localization
Tim TangRSS2021Get to the Point: Learning Lidar Place Recognition and Metric Localisation Using Overhead Imagery
Visesh ChariICCV2021Multi-Hypothesis Pose Networks: Rethinking Top-Down Pose Estimation
Ankit LaddhaCORL2020Liranet: End-to-end trajectory prediction using spatio-temporal radar fusion
Ankit LaddhaICRA / RA-L2020Laserflow: Efficient and probabilistic object detection and motion forecasting
Jason ZiglarCVPR2020What You See is What You Get: Exploiting Visibility for 3D Object Detection
Nick DePalmaRSS2020Leveraging knowledge asymmetries to evaluate synthesized gesture based communication in human-robot interaction
Ryan TurnerNeurIPS2020Analysis of the Black-Box Optimization Challenge 2020
Sudipta SinhaCVPR2020ActiveMoCap: Optimized Viewpoint Selection for Active Human Motion Capture
Sudipta SinhaRA-L2020Towards Privacy-Preserving Ego-Motion Estimation using an Extremely Low-Resolution Camera
Tim TangICRA2020RSL-Net: Localising in Satellite Images From a Radar on the Ground
Tim TangRSS2020Self-Supervised Localisation between Range Sensors and Overhead Imagery
Ankit LaddhaCVPR2019Lasernet: An efficient probabilistic 3d object detector for autonomous driving
Ankit LaddhaCVPR2019Sensor fusion for joint 3d object detection and semantic segmentation
Ryan TurnerICML2019Metropolis-Hastings Generative Adversarial Networks
Ryan TurnerNeurIPS2019Scalable Global Optimization via Local Bayesian Optimization
Sudipta SinhaCVPR2019Privacy Preserving Image-Based Localization
Sudipta SinhaCVPR2019Revealing Scenes by Inverting Structure from Motion Reconstructions
Sudipta SinhaICCV2019Privacy Preserving Image Queries for Camera Localization
Tim TangICRA2019A White-Noise-on-Jerk Motion Prior for Continuous-Time Trajectory Estimation on SE(3)
Visesh ChariCVPR2019Learning to Generate Synthetic Data via Compositing
Visesh Chari3DV2019Towards accurate 3D human body reconstruction from silhouettes
Shaojun ZhuIJCAI2018Fast Model Identification via Physics Engines for Data-Efficient Policy Search
Shaojun Zhu IROS2018Efficient Model Identification for Tensegrity Locomotion
Sudipta SinhaCVPR2018Real-Time Seamless Single Shot 6D Object Pose Prediction
Sudipta SinhaECCV2018Learn-to-Score: Efficient 3D Scene Exploration by Predicting View Utility
Sudipta SinhaECCV2018Learning to Fuse Proposals from Multiple Scanline Optimizations in Semi-Global Matching
Visesh ChariECCV2018A Unified View-Graph Selection Framework for Structure from Motion
Alvaro Collet RomeaSIGGRAPH2017Spatiotemporal atlas parameterization for evolving meshes
Ankit LaddhaCVIU and EMNLP2017Resolving vision and language ambiguities together: Joint segmentation & prepositional attachment resolution in captioned scenes
Hatem AlismailICCV2017Deltille grids for geometric camera calibration
Jason ZiglarJournal of Field Robotics2017Team VALOR's ESCHER: A Novel Electromechanical Biped for the DARPA Robotics Challenge
Kevin WyffelsJournal of Advances in Information Fusion2017Priority-Based Tracking of Extended Objects
Ryan TurnerUAI2017How Well Does Your Sampler Really Work?
Sudipta SinhaCVPR2017Flight Dynamics-based Recovery of a UAV Trajectory using Ground Cameras
Sudipta SinhaCVPR2017Fast Multi-frame Stereo Scene Flow with Motion Segmentation
Sudipta SinhaICCV2017Submodular Trajectory Optimization for Aerial 3D Scanning
Sudipta SinhaTransactions on Pattern Analysis and Machine Intelligence2017Robust Multiview Photometric Stereo using Planar Mesh Parameterization
Sudipta SinhaTransactions on Pattern Analysis and Machine Intelligence2017Multiview Rectification of Folded Documents
Alvaro Collet RomeaSIGGRAPH2016Motion graphs for unstructured textured meshes
Ankit LaddhaIV2016Map-supervised road detection
Hatem Alismail3DV2016Robust tracking in low light and sudden illumination changes
Hatem AlismailACCV2016Enhancing direct camera tracking with dense feature descriptors
Hatem AlismailACCV2016Photometric bundle adjustment for vision-based slam
Hatem AlismailRAL2016Direct visual odometry in low light using binary descriptors
Kevin WyffelsTransactions on Robotics2016Precision Tracking via joint detailed shape estimation of arbitrary extended objects
Shaojun Zhu NeurIPS workshop 2016A Physically-grounded and Data-efficient Approach to Motion Prediction using Black-box Optimization
Sudipta SinhaCVPR2016Joint Recovery of Dense Correspondence and Cosegmentation in Two Images
Visesh ChariICRA2016Monocular Reconstruction of Vehicles: Combining SLAM with Shape Priors
Visesh ChariICRA2016Rolling shutter and motion blur removal for depth cameras
Alvaro Collet RomeaInternational Journal of Robotics Research2015HerbDisc: Towards Lifelong Robotic Object Discovery
Alvaro Collet RomeaSIGGRAPH2015High-Quality Streamable Free-Viewpoint Video
Ankit LaddhaCVPR2015Active learning for structured probabilistic models with histogram approximation
Hatem AlismailIJRR2015Visual mapping for natural gas pipe inspection
Hatem AlismailJFR2015Automatic calibration of spinning actuated lidar internal parameters
Kevin WyffelsICRA2015Joint tracking and nonparametric shape estimation of arbitrary extended objects
Kevin WyffelsTransactions on Robotics2015Negative Information for occlusion reasoning in dynamic extended multiobject tracking
Sudipta SinhaInternational Journal of Robotics Research2015Real-time monocular image-based 6-DoF localization
Visesh ChariCVPR2015On pairwise cost for multi-object network flow tracking
Visesh ChariIROS2015Dynamic body vslam with semantic constraints
Hatem AlismailICRA2014Continuous Trajectory Estimation for 3D SLAM from Actuated Lidar
Ryan TurnerNeurIPS2014A Complete Variational Tracker
Alvaro Collet RomeaICRA2013Exploiting Domain Knowledge for Object Discovery
Tyler GaraasICCV2013Tracking an RGB-D Camera Using Points and Planes
Alvaro Collet RomeaProceedings of the IEEE2012Herb 2.0: Lessons learned from developing a mobile manipulator for the home
Tyler GaraasECCV2012Monocular Visual Odometry and Dense 3d Reconstruction for On-Road Vehicles
Visesh ChariCVPR2012A theory of multi-layer flat refractive geometry
Visesh ChariICRA2012Convex bricks: A new primitive for visual hull modeling and reconstruction
Visesh ChariIROS2010Multiple plane tracking using unscented kalman filter

Join Our Team

We're building the future of autonomous freight and looking for exceptional talent. From cutting-edge perception algorithms to robust ML infrastructure, we have opportunities across the full autonomy stack — and a transparent, engineer-friendly interview process.

Open Positions

Perception & Computer Vision
Detection, tracking, calibration
Robotics and Planning
Motion planning, localization, mapping
ML Infrastructure
Training pipelines, data systems
Systems & Platform
Edge computing, cloud integration

Internships

• Autolabeling
• 3D Perception/Tracking/SLAM
• Long Range Perception
• Methods to Introspect Data
• Automatic Mapping
• Prediction
• Deep Decision Making
• Deep World Building

How We Interview

We know the best candidates are evaluating us too. Here's our transparent, engineer-friendly approach:

Streamlined Process

Engineer-led, efficient interviews

Technical Deep Dives

Real problems, not LeetCode

Meet the Team

Connect with future teammates

3

Stages

  • Recruiter Call
  • Technical Screen
  • Virtual Onsite
3

Weeks

We can move as fast as your schedule allows! Most candidates complete the process in about 3 weeks with timely cooperation.
3

Criteria

  • Hard Skills: coding & systems
  • Soft Skills: problem solving
  • Culture Fit: our values

Visit Stack AV at ICCV

Booth #230

Connect with us for exclusive swag, engaging technical conversations, and the chance to meet our team. Interested in a more in-depth discussion about our technology or potential career paths? Schedule a dedicated meeting—we’d love to explore the possibilities with you.

Free Swag & Prizes!

Stop by our booth to grab exclusive Stack AV merchandise and enter daily prize drawings!
Stack AV Sticker
Stickers
Stack AV Swag
T-shirts
Plus daily surprises at our booth!