ΑΙhub.org
deep dive
Bottom-up top-down detection transformers for open vocabulary object detection
ML@CMU
23 Jan 2023
We introduce a model that detects all objects that a phrase mentions.
Causal confounds in sequential decision making
ML@CMU
06 Dec 2022
Using techniques from causal inference, we derive provably correct and scalable algorithms for sequential decision making in certain settings.
Tackling diverse tasks with neural architecture search
ML@CMU
24 Oct 2022
We developed a Neural Architecture Search method that generates and trains task-specific convolutional neural networks.
Tracking any pixel in a video
ML@CMU
17 Oct 2022
We propose Persistent Independent Particles (PIPs), a new particle video method to track pixels in a video.
Keeping learning-based control safe by regulating distributional shift
BAIR blog
30 Sep 2022
We propose a new framework to reason about the safety of a learning-based controller with respect to its training distribution.
Recurrent model-free RL can be a strong baseline for many POMDPs
ML@CMU
23 Sep 2022
Considering an approach for dealing with realistic problems with noise and incomplete information.
Reverse engineering the NTK: towards first-principles architecture design
BAIR blog
12 Sep 2022
We propose a paradigm for bringing some principle to the art of architecture design.
Galaxies on graph neural networks
ML@CMU
05 Sep 2022
Using Graph Neural Networks, we trained Generative Adversarial Networks to correctly predict the coherent orientations of galaxies in a state-of-the-art cosmological simulation.
auton-survival: An open-source package for regression, counterfactual estimation, evaluation and phenotyping censored time-to-event data
ML@CMU
22 Aug 2022
We present auton-survival – a comprehensive Python code repository of user-friendly, machine learning tools for working with censored time-to-event data.
Why do policy gradient methods work so well in cooperative MARL? Evidence from policy representation
BAIR blog
15 Aug 2022
We show how policy gradient methods can converge to an optimal policy in certain cases, and that they can learn multi-modal policies.
Does AutoML work for diverse tasks?
ML@CMU
01 Aug 2022
Can the available AutoML tools quickly and painlessly attain near-expert performance on diverse learning tasks?
FIGS: Attaining XGBoost-level performance with the interpretability and speed of CART
BAIR blog
12 Jul 2022
In this blog post we cover a new method for fitting an interpretable model that takes the form of a sum of trees.
Deep attentive variational inference
ML@CMU
24 Jun 2022
The expressivity of current deep probabilistic models can be improved by selectively prioritizing statistical dependencies between latent variables that are potentially distant from each other.
Rethinking human-in-the-loop for artificial augmented intelligence
BAIR blog
17 Jun 2022
How do we build and evaluate an AI system for real-world applications?
Bootstrapped meta-learning – an interview with Sebastian Flennerhag
Lucy Smith
07 Jun 2022
ICLR2022 award winner tells us about how he and co-authors approached the meta-learning problem.
Designing societally beneficial reinforcement learning systems
BAIR blog
31 May 2022
Studying the risks associated with using reinforcement learning for real-world applications.
An experimental design perspective on model-based reinforcement learning
ML@CMU
19 May 2022
We propose a simple algorithm that is able to solve a wide variety of control tasks.
Should I use offline RL or imitation learning?
BAIR blog
17 May 2022
In this blog post, we aim to understand if, when and why offline RL is a better approach for tackling a variety of sequential decision-making problems.
Offline RL made easier: no TD learning, advantage reweighting, or transformers
BAIR blog
03 May 2022
We try to identify the essential elements of offline RL via supervised learning.
Unsupervised skill discovery with contrastive intrinsic control
BAIR blog
01 Apr 2022
Unsupervised reinforcement learning (RL), where RL agents pre-train with self-supervised rewards, is an emerging paradigm for developing RL agents that are capable of generalization.
Assessing generalization of SGD via disagreement
ML@CMU
21 Mar 2022
We demonstrate that a simple procedure can accurately estimate the generalization error with only unlabeled data.
imodels: leveraging the unreasonable effectiveness of rules
BAIR blog
14 Mar 2022
imodels provides a simple unified interface and implementation for many state-of-the-art interpretable modeling techniques, particularly rule-based methods.
Why spectral normalization stabilizes GANs: analysis and improvements
ML@CMU
07 Mar 2022
We investigate the training stability of generative adversarial networks (GANs).
The unsupervised reinforcement learning benchmark
BAIR blog
14 Feb 2022
We consider the unsupervised RL problem - how do we learn useful behaviors without supervision and then adapt them to solve downstream tasks quickly?
Improving RL with lookahead: learning off-policy with online planning
ML@CMU
11 Feb 2022
We suggest using a policy that looks ahead using a learned model to find the best action sequence.
Sequence modeling solutions for reinforcement learning problems
BAIR blog
03 Feb 2022
We tackle large-scale reinforcement learning problems with the toolbox of sequence modeling.
An energy-based perspective on learning observation models
ML@CMU
21 Jan 2022
We propose a conceptually novel approach to mapping sensor readings into states.
Which mutual information representation learning objectives are sufficient for control?
BAIR blog
10 Jan 2022
How can we best design representation learning objectives?
Understanding user interfaces with screen parsing
ML@CMU
03 Jan 2022
We introduce the problem of screen parsing, which we use to predict structured user interface models from visual information.
Bridge data: boosting generalization of robotic skills with cross-domain datasets
BAIR blog
30 Dec 2021
With our proposed dataset and multi-task, multi-domain learning approach, we have shown one potential avenue for making diverse datasets reusable in robotics.
Why generalization in RL is difficult: epistemic POMDPs and implicit partial observability
BAIR blog
21 Dec 2021
In this blog post, we will aim to explain why generalization in RL is fundamentally hard, even in theory.
Designs from data: offline black-box optimization via conservative training
BAIR blog
10 Dec 2021
In this post, we discuss offline model-based optimization and some recent advances in this area.
A first-principles theory of neural network generalization
BAIR blog
22 Nov 2021
Find out more about research trying to shed light on the workings of deep neural networks.
Compression, transduction, and creation: a unified framework for evaluating natural language generation
ML@CMU
18 Nov 2021
Our framework classifies language generation tasks into compression, transduction, and creation.
Making RL tractable by learning more informative reward functions: example-based control, meta-learning, and normalized maximum likelihood
BAIR blog
15 Nov 2021
This article presents MURAL, a method for learning uncertainty-aware rewards for RL.
PICO: Pragmatic compression for human-in-the-loop decision-making
BAIR blog
05 Nov 2021
In this post, we outline a pragmatic compression algorithm called PICO.
