Videos

See AI2's full collection of videos on our YouTube channel.
Viewing 1-10 of 216 videos
  • Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics Thumbnail

    Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

    This video describes the Action Adaptive Policy by Zeng et al. (ICLR 2023). In the video, we discuss the formulation of motion drifts in point navigation and object navigation tasks. Additionally, we introduce the Action Adaptive Policy (AAP) to address these motion drifts. Finally, we demonstrate that AAP…
  • Recycling finetuned models to pretrain: on loss spaces, fusing and evolving pretraining Thumbnail

    Recycling finetuned models to pretrain: on loss spaces, fusing and evolving pretraining

    March 7, 2023  |  Leshem Choshen
    This work will discuss the recent advancement in recycling finetuned models – Harnessing the data and computation invested in one or more models to collaboratively improve the pre-trained model they originated form. The work will also touch on our initial understandings of how and why fusing several models by…
  • Robot learning and perception for contact-rich manipulation Thumbnail

    Robot learning and perception for contact-rich manipulation

    March 2, 2023  |  Samarth Brahmbhatt
    Abstract: Object rearrangement will become an important skill for collaborative robots as they increasingly operate in unstructured environments. Rearrangement involves grasping, goal-conditioned navigation, and placement. In this talk, I will present our latest work, which focuses on placement. We learn a…
  • Empowering Human-like Decision Making in AI Models through Explanations Thumbnail

    Empowering Human-like Decision Making in AI Models through Explanations

    February 22, 2023  |  Ramasamy Selvaraju Ramprasaath
    Abstract: Deep neural networks have achieved remarkable results in several Computer Vision tasks, but their increasing complexity poses challenges in terms of interpretability. In this talk, I will present my research on explainability in deep learning models, ranging from convolutional neural networks (CNNs) to…
  • Environment-oriented modeling for grounded NLP and collective intelligence systems Thumbnail

    Environment-oriented modeling for grounded NLP and collective intelligence systems

    February 21, 2023  |  Ronen Tamari
    Abstract: “Ask not what's inside your head, but what's your head inside of” — W.M. Mace, 1977 In contrast to classical cognitive science which studied brains in isolation, ecological cognitive science accounts focus on the role of the body and external environment in shaping cognition. In this talk I will…
  • Understanding and Improving Compositional Generalization Thumbnail

    Understanding and Improving Compositional Generalization

    February 10, 2023  |  Ben Bogin
    Pre-trained language models perform well on a large variety of question-answering tasks, but they still often fail in the compositional generalization setup, where models are tested on unseen compositions of reasoning skills. In this talk, I will go over three research directions that address this challenge. In…
  • No Language Left Behind Unlocking Text Data for Under Resourced  Thumbnail

    No Language Left Behind Unlocking Text Data for Under Resourced

    February 9, 2023  |  Shruti Rijhwani
    NLP systems are limited by the availability of text data, and because machine-readable text exists only in a few hundred languages, most of the world’s languages are under-represented in modern language technologies. Text data exists in many more languages! However, it is locked away in printed books and…
  • Artificial Intelligence and Ethics: Towards a Robust Normative Framework Thumbnail

    Artificial Intelligence and Ethics: Towards a Robust Normative Framework

    February 8, 2023  |  S. Matthew Liao
    Abstract: As AI technologies continue to advance, questions about the ethics of AI become more pressing than ever. In this talk, I aim to outline some of the key issues in the study of AI ethics, identify some of the core claims that have been made, and propose an ethical framework that can help us guide these…
  • What Do NLP Researchers Believe? Results of the NLP Community Metasurvey Thumbnail

    What Do NLP Researchers Believe? Results of the NLP Community Metasurvey

    Abstract: I will present the results of the NLP Community Metasurvey (nlpsurvey.net). This was a questionnaire that we ran from May to June 2022 which elicited the opinions of NLP researchers on controversial issues, including industry influence in the field, concerns about AGI, and ethics. Our results put…
  • Global storm-resolving climate simulation in Python Thumbnail

    Global storm-resolving climate simulation in Python

    December 14, 2022  |  Oliver Fuhrer
    This video shows an animation of a climate simulation done with a Python implementation of NOAA's climate model FV3GFS on the Piz Daint supercomputer. Even thought the code is implemented in Python, it runs 3.9x faster than the original implementation in Fortran. This is due to the help of a domain-specific…