ΑΙhub.org
deep dive
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
Sophie Henning and Annemarie Friedrich
RLPrompt: Optimizing discrete text prompts with reinforcement learning
We propose an efficient discrete prompt optimization approach with reinforcement learning.
07 March 2023, by
ML@CMU
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
BAIR blog
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
Valentin De Bortoli
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
ML@CMU
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
ML@CMU
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
ML@CMU
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
ML@CMU
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
BAIR blog
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
ML@CMU
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
BAIR blog
Galaxies on graph neural networks
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.
05 September 2022, by
ML@CMU
auton-survival: An open-source package for regression, counterfactual estimation, evaluation and phenotyping censored time-to-event data
We present auton-survival – a comprehensive Python code repository of user-friendly, machine learning tools for working with censored time-to-event data.
22 August 2022, by
ML@CMU
Why do policy gradient methods work so well in cooperative MARL? Evidence from policy representation
We show how policy gradient methods can converge to an optimal policy in certain cases, and that they can learn multi-modal policies.
15 August 2022, by
BAIR blog
Does AutoML work for diverse tasks?
Can the available AutoML tools quickly and painlessly attain near-expert performance on diverse learning tasks?
01 August 2022, by
ML@CMU
FIGS: Attaining XGBoost-level performance with the interpretability and speed of CART
In this blog post we cover a new method for fitting an interpretable model that takes the form of a sum of trees.
12 July 2022, by
BAIR blog
Deep attentive variational inference
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.
24 June 2022, by
ML@CMU
Rethinking human-in-the-loop for artificial augmented intelligence
How do we build and evaluate an AI system for real-world applications?
17 June 2022, by
BAIR blog
Bootstrapped meta-learning – an interview with Sebastian Flennerhag
ICLR2022 award winner tells us about how he and co-authors approached the meta-learning problem.
07 June 2022, by
Lucy Smith
Designing societally beneficial reinforcement learning systems
Studying the risks associated with using reinforcement learning for real-world applications.
31 May 2022, by
BAIR blog
An experimental design perspective on model-based reinforcement learning
We propose a simple algorithm that is able to solve a wide variety of control tasks.
19 May 2022, by
ML@CMU
Should I use offline RL or imitation learning?
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.
17 May 2022, by
BAIR blog
Offline RL made easier: no TD learning, advantage reweighting, or transformers
We try to identify the essential elements of offline RL via supervised learning.
03 May 2022, by
BAIR blog
Unsupervised skill discovery with contrastive intrinsic control
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.
01 April 2022, by
BAIR blog
Assessing generalization of SGD via disagreement
We demonstrate that a simple procedure can accurately estimate the generalization error with only unlabeled data.
21 March 2022, by
ML@CMU
imodels: leveraging the unreasonable effectiveness of rules
imodels provides a simple unified interface and implementation for many state-of-the-art interpretable modeling techniques, particularly rule-based methods.
14 March 2022, by
BAIR blog
Why spectral normalization stabilizes GANs: analysis and improvements
We investigate the training stability of generative adversarial networks (GANs).
07 March 2022, by
ML@CMU
The unsupervised reinforcement learning benchmark
We consider the unsupervised RL problem - how do we learn useful behaviors without supervision and then adapt them to solve downstream tasks quickly?
14 February 2022, by
BAIR blog
Improving RL with lookahead: learning off-policy with online planning
We suggest using a policy that looks ahead using a learned model to find the best action sequence.
11 February 2022, by
ML@CMU
Sequence modeling solutions for reinforcement learning problems
We tackle large-scale reinforcement learning problems with the toolbox of sequence modeling.
03 February 2022, by
BAIR blog
