What Data Robots Need: From Co-Designed Handheld Capture to Fleet-Scale Flywheels
Talk, Extropic, Waltham, MA
Invited talk at Extropic’s Boston office, presenting the same material given at the It’s the Demos workshop at RSS 2026.
Talks and presentations
Tactile Sensing for Robotic Foundation Models (Workshop Co-Organizer)
Conference Organizing, RSS 2026 Workshop, Sydney, Australia
Co-organizing the Tactile Sensing for Robotic Foundation Models workshop at RSS 2026 in Sydney, Australia. The workshop explores what role tactile sensing should play in the emerging era of robotic foundation models and large-scale data collection.
What Data Robots Need: From Co-Designed Handheld Capture to Fleet-Scale Flywheels
Talk, RSS 2026 Workshop: It's the Demos, Sydney, Australia
Invited talk at the It’s the Demos workshop (A Deep Look at the Role of Demonstration Quality in Imitation-Based Robot Manipulation) at RSS 2026 in Sydney, Australia.
Why Robots? Data-Driven Manipulation for the World’s Hardest Sorting Problem
Talk, Brown University, Providence, RI
Guest lecture in Stefanie Tellex’s class at Brown University on robotic manipulation for landfill restoration. The talk covered multimodal sensing (force, audio, spectroscopic), the capability gap between warehouse robots and unstructured-environment robots, and why landfill sorting may be the hardest data collection problem in robotics.
New England Manipulation Symposium (NEMS) 2025
Talk, MIT, Cambridge, MA, Cambridge, MA
NEMS 2025 was an amazing event featuring the best and brightest minds of New England.
We had over 140 attendees, with 18 different talks, two keynote speakers, and 44 posters.
Thank you to my co-organizers Lael Odhner and Kait Becker.
Lions in AI Expert Panel Discussion
Talk, Columbia Alumni Association of Boston, Boston, MA
I had so much fun being on the Lions in AI panel last week!
Barnet Sherman moderated a fantastic discussion with a series of expert panelists in AI and myself.
We received thought-provoking questions about AI and society.
New England Manipulation Symposium (NEMS) 2025 - Co-Organizer
Conference Organization, MIT, Cambridge, MA
Co-organized the New England Manipulation Symposium (NEMS) 2025 at MIT with Lael Odhner and Kaitlyn Becker. Coordinated paper acceptances, speaker scheduling, and venue logistics for the regional robotics conference.
Future of Robotics Interview with Dr. Waku
Talk, Dr. Waku YouTube Channel, Online
I was featured on Dr. Waku’s channel, discussing the future of robotics and the importance of data-driven methods.
Thank you, Dr. Waku, for having me on. I am really excited about how this turned out!
The Future of Intelligent Robotics - Dr. Waku Interview
Media Interview, Dr. Waku YouTube Channel, Online
Featured interview discussing robotics’ “ChatGPT moment” and the future of embodied AI. Explored how foundation models and large-scale data collection are transforming robot learning.
Foundation Models for Robotics - Duke University Talk
Talk, Duke University - Mechanical Engineering Department, Durham, NC
In February 2024, I was invited to give a talk at Duke University on Foundation Models for Robotics.
Thank you to Boyuan Chen for hosting my visit.
It was incredibly cool to see the impressive work being done by the professors in the Mechanical Engineering department.
Tips on Wrapping up Your PhD and Surviving the Job Hunt
Talk, Podcast hosted by Ding Li, Online
In this episode, we discuss strategies for wrapping up your PhD dissertation and preparing for life after grad school.
Hosted by Ding Li, with guests Henrique Maia and David Watkins.
Foundation Models for Robotics - Brown University Talk
Talk, Brown University, Providence, RI
I had the great fortune of giving a talk at Brown University about the exciting work we at RAI Institute are doing with Foundation Models.
Thanks to George Konidaris and Stefanie Tellex for inviting me and organizing the event.
This Team won the Minecraft RL BASALT Challenge! (Paper Explanation & Interview with the authors)
Talk, Yannic Kilcher Youtube, Boston, MA
ROAM Lab: Learning Mobile Manipulation
Talk, ROAM Lab Weekly Meeting, New York, New York
CAIR Lab: Learning Mobile Manipulation
Talk, CAIR Lab Weekly Meeting, New York, New York
IROS 2020: Learning Your Way Without Map or Compass
Talk, IROS 2020, New York, New York
Demystifying the Dissertation
Talk, Columbia University Zoom, New York, New York
Thesis Proposal: Learning Mobile Manipulation
Talk, Columbia University, New York, New York
Providing mobile robots with the ability to manipulate objects has, despite decades of research, remained a challenging problem. The problem is approachable in constrained environments where there is ample prior knowledge of the environment and objects that will be manipulated. The challenge is in building systems that scale beyond specific situational instances and gracefully operate in novel conditions. In the past, heuristic and simple rule based strategies were used to accomplish tasks such as scene segmentation or reasoning about occlusion. These heuristic strategies work in constrained environments where a roboticist can make simplifying assumptions about everything from the geometries of the objects to be interacted with, level of clutter, camera position, lighting, and a myriad of other relevant variables. In this thesis we will demonstrate how a system for mobile manipulation can be built that is robust to changes in these variables. This robustness will be enabled by recent simultaneous advances in the fields of Big Data, Deep Learning, and Simulation. The ability of simulators to create realistic sensory data enables the generation of massive corpora of labeled training data for various grasping and navigation based tasks. We will show that it is now possible to build systems that works in the real world trained using deep learning almost entirely on synthetic data. The ability to train and test on synthetic data allows for quick iterative development of new perception, planning and grasp execution algorithms that work in a large number of environments.
Research Talk for Harlem Children’s Zone STEM Exposure
Talk, Columbia University, New York, New York
Learning Your Way Talk for NERC
Talk, NERC, Philadelphia, Pennsylvania
Learning Your Way Talk for NYU Reading Group
Talk, NYU Reading Group, Brooklyn, New York
Emptor Lightning Talks: Visual Tactile Completion
Talk, Emptor Lightning Talks, New York, New York
Visual Tactile Grasping
Talk, Samsung Research NYC, New York, New York
Presented my work on visual tactile grasping. slide
Odefi Pitch at Columbia IBM Blockchain Accelerator Demo Day
Talk, Columbia University, New York, New York
Candidacy Exam: Simulation for Real World Robotics
Talk, Candidacy Exam, New York, New York
Abstract
Real world robotics is a multifarious process spanning several fields including simulation, semantic/scene understanding, reinforcement learning, domain randomization, just to name a few. Ideally simulators would accurately capture the real world perfectly in a much faster capacity allowing for a predictive power of how a robot will interact with its environment. Unfortunately, simulators neither have the speed nor accuracy to support this. Simulators, such as Gazebo, Webots, and OpenRave, are supplemented with machine learned models of their environment to solve specific tasks such as scene understanding and path planning. This can be compared to a physical only solution which can be costly in terms of price and time. Advances in virtual reality allow for new ways for humans to provide training data for robotic systems in simulation. Using modern datasets such as SUNCG and Matterport3D we now have more ability than ever to train robots in virtual environments. Through understanding modern applications of simulations, better robotic platforms can be designed to solve some of the most pressing challenges of modern robotics.
Using Simulation to Enable Generated Art and Robotics
Talk, Blackbox Lightning Talks, New York, New York
Multi-Modal Geometric Learning for Grasping and Manipulation (Poster)
Talk, Columbia Data Science Day, New York, New York
ROS Tutorial
Talk, Columbia University, Humanoid Robotics, New York, New York
Providing Context to Startup Culture
Talk, Columbia University, Cultural Psychology, New York, New York