• about
  • resources
  • contribute
  • republishing
    • ☰
  • news
  • articles
  • opinions
  • education

    • ΑΙhub.org

    deep dive


    Beyond the mud: Datasets, benchmarks, and methods for computer vision in off-road racing
    Off-road motorcycle racing poses unique challenges that push the boundaries of what existing computer vision systems can handle
    17 April 2024, by

    Modeling extremely large images with xT
    Introducing a new framework to model large images on contemporary GPUs while aggregating global context with local details.
    08 April 2024, by

    The shift from models to compound AI systems
    State-of-the-art AI results are increasingly obtained by compound systems with multiple components, not just monolithic models.
    15 March 2024, by

    Unlocking the potential of entity-centric knowledge graphs: transforming healthcare and beyond
    The concept of entity-centric knowledge graphs holds promise in reshaping how we organize, access, and leverage data.
    27 February 2024, by and

    On noisy evaluation in federated hyperparameter tuning
    Our work explores key sources of noise and shows that even small amounts of noise can have a significant impact on tuning methods.
    12 January 2024, by

    Asymmetric certified robustness via feature-convex neural networks
    We propose the asymmetric certified robustness problem, which requires certified robustness for only one class and reflects real-world adversarial scenarios.
    14 December 2023, by



    Goal representations for instruction following
    How can we reconcile the ease of specifying tasks through natural language-based approaches with the performance improvements of goal-conditioned learning?
    23 November 2023, by

    A comprehensive survey on rare event prediction
    We review the rare event prediction literature and highlight open research questions and future directions in the field.
    22 November 2023, by , and

    Test-time adaptation with slot-centric models
    Improving out-of-distribution scene decomposition accuracy.
    25 September 2023, by

    Training diffusion models with reinforcement learning
    We show how diffusion models can be trained on downstream objectives directly using reinforcement learning.
    15 September 2023, by

    A ‘black box’ AI system has been influencing criminal justice decisions for over two decades – it’s time to open it up
    Melissa Hamilton and Pamela Ugwudike investigate the use of automated decision-making systems in courts and prisons.
    11 August 2023, by

    On the stepwise nature of self-supervised learning
    Presenting a mathematical picture of the training process of large-scale SSL methods.
    01 August 2023, by

    Navigating to objects in the real world
    Research shows that modular learning is a reliable approach to navigate to objects.
    24 July 2023, by

    Generating 3D molecular conformers via equivariant coarse-graining and aggregated attention
    Introducing a variational encoder for molecular conformer generation.
    14 July 2023, by

    GPT-4 + Stable-Diffusion = ?: Enhancing prompt understanding of text-to-image diffusion models with large language models
    Our LLM-grounded model delivers improved prompt understanding in cases including negation, numeracy, and spatial relationships.
    26 June 2023, by

    On privacy and personalization in federated learning: a retrospective on the US/UK PETs challenge
    Studying the use of differential privacy in personalized, cross-silo federated learning.
    05 June 2023, by

    TIDEE: An embodied agent that tidies up novel rooms using commonsense priors
    We introduce a new benchmark to test agents in their ability to clean up messy scenes without any human instruction.
    28 April 2023, by

    Koala: A dialogue model for academic research
    In this post, we introduce Koala, a chatbot trained by fine-tuning Meta’s LLaMA on dialogue data gathered from the web.
    18 April 2023, by

    Are model explanations useful in practice? Rethinking how to support human-ML interactions
    This post describes a workflow for evaluating XAI methods, how this workflow was instantiated in two domains, and insights from these efforts.
    14 April 2023, by

    Methods for addressing class imbalance in deep learning-based natural language processing
    This blogpost gives an overview of class imbalance in NLP and surveys methods for addressing this.
    30 March 2023, by and

    RLPrompt: Optimizing discrete text prompts with reinforcement learning
    We propose an efficient discrete prompt optimization approach with reinforcement learning.
    07 March 2023, by

    Fully autonomous real-world reinforcement learning with applications to mobile manipulation
    A system that learns to clean up a room directly with a real robot via continual learning.
    07 February 2023, by

    Riemannian score-based generative modelling
    The winners of a NeurIPS 2022 best paper award write about their work on generative modelling.
    01 February 2023, by

    Bottom-up top-down detection transformers for open vocabulary object detection
    We introduce a model that detects all objects that a phrase mentions.
    23 January 2023, by

    Causal confounds in sequential decision making
    Using techniques from causal inference, we derive provably correct and scalable algorithms for sequential decision making in certain settings.
    06 December 2022, by

    Tackling diverse tasks with neural architecture search
    We developed a Neural Architecture Search method that generates and trains task-specific convolutional neural networks.
    24 October 2022, by

    Tracking any pixel in a video
    We propose Persistent Independent Particles (PIPs), a new particle video method to track pixels in a video.
    17 October 2022, by

    Keeping learning-based control safe by regulating distributional shift
    We propose a new framework to reason about the safety of a learning-based controller with respect to its training distribution.
    30 September 2022, by

    Recurrent model-free RL can be a strong baseline for many POMDPs
    Considering an approach for dealing with realistic problems with noise and incomplete information.
    23 September 2022, by

    Reverse engineering the NTK: towards first-principles architecture design
    We propose a paradigm for bringing some principle to the art of architecture design.
    12 September 2022, by

     
    next page →



    ↑
  • news
  • articles
  • opinions
  • education
  • about
  • resources
  • contribute
  • republishing
  • RSS
  • linkedin
  • facebook
  • twitter
  • Youtube

    • AIhub is supported by:






    ©2024 - Association for the Understanding of Artificial Intelligence


     










    ©2021 - ROBOTS Association