Videos

See AI2's full collection of videos on our YouTube channel.
Viewing 11-20 of 202 videos
  • Why Natural Language is the Right Vehicle for Complex Reasoning Thumbnail

    Why Natural Language is the Right Vehicle for Complex Reasoning

    May 11, 2022  |  Greg Durrett
    Abstract: Despite their widespread success, end-to-end transformer models consistently fall short in settings involving complex reasoning. Transformers trained on question answering (QA) tasks that seemingly require multiple steps of reasoning often achieve high performance by taking "reasoning shortcuts." We…
  • Data Leverage: A Framework for Empowering the Public and Mitigating Harms of AI

    May 10, 2022  |  Nicholas Vincent
    Many powerful computing technologies rely on both implicit and explicit data contributions from the public. This dependency suggests a potential source of leverage for the public in its relationship with technology companies: by reducing, stopping, redirecting, or otherwise manipulating data contributions, a…
  • Doing for our robots what nature did for us Thumbnail

    Doing for our robots what nature did for us

    April 29, 2022  |  Leslie Pack Kaelbling
    We, as robot engineers, have to think hard about our role in the design of robots and how it interacts with learning, both in "the factory" (that is, at engineering time) and in "the wild" (that is, when the robot is delivered to a customer). I will share some general thoughts about the strategies for robot…
  • Cross-Task Generalization via Natural Language Crowdsourcing Instructions Thumbnail

    Cross-Task Generalization via Natural Language Crowdsourcing Instructions

    April 21, 2022  |  Swaroop Mishra
    This video explains the paper "https://arxiv.org/abs/2104.08773". Abstract:Humans (e.g., crowdworkers) have a remarkable ability in solving different tasks, by simply reading textual instructions that define them and looking at a few examples. Despite the success of the conventional supervised learning on…
  • Generalization for Robot Learning In The Wild Thumbnail

    Generalization for Robot Learning In The Wild

    April 15, 2022  |  Deepak Pathak
    How can we train a robot that can generalize to perform thousands of tasks in thousands of environments? This question underscores the holy grail of robot learning, more generally machine learning, research. Current AI systems are incredibly specific in that they only perform the tasks they are trained for and…
  • Robots Need To Reduce, Reuse, and Recycle Thumbnail

    Robots Need To Reduce, Reuse, and Recycle

    April 1, 2022  |  Chelsea Finn
    Despite numerous successes in deep robotic learning over the past decade, the generalization and versatility of robots across environments and tasks has remained a major challenge. This is because much of reinforcement and imitation learning research trains agents from scratch in a single or a few environments…
  • Synthetic Data for Language-Guided Agents Thumbnail

    Synthetic Data for Language-Guided Agents

    March 18, 2022  |  Peter Anderson
    Recent advances in vision and language modeling have been powered by truly massive datasets, often mined from the web. Instruction-following robots will also require large amounts of data to train and evaluate. However, images/videos/documents found on the web do not satisfy the needs of embodied agents, and data…
  • Soft Robotics and AI towards Embodied Intelligence Thumbnail

    Soft Robotics and AI towards Embodied Intelligence

    March 4, 2022  |  Fumiya Iida
    Soft robotics research has made considerable progress in many areas of robotics technologies based on deformable functional materials, including locomotion, manipulation, and other morphological adaptation such as self-healing, self-morph, and mechanical growth. While these technologies open up many new robotics…
  • A Flexible Framework for Machine Learning

    March 2, 2022  |  Ferran Alet
    In this last decade, we have seen a lot of progress in AI and Machine Learning using different variations on a single recipe: we specify a task as learning a function mapping inputs to outputs and we train a single neural network to approximate it. In this talk, I will show that this one NN per task framework can…
  • The Future is Hear: Advances in Computational Audition and Sound Manipulation Thumbnail

    The Future is Hear: Advances in Computational Audition and Sound Manipulation

    December 1, 2021  |  Bryan Pardo
    Abstract: Computer Audition is the sonic analog to Computer Vision and encompasses much more than just speech to text. Northwestern University’s Interactive Audio Lab (IAL), headed by Prof. Bryan Pardo, is a world leader in Computer Audition. IAL develops new techniques and technologies for identifying sound…