ΑΙhub.org
deep dive
An energy-based perspective on learning observation models
We propose a conceptually novel approach to mapping sensor readings into states.
21 January 2022, by
ML@CMU
Which mutual information representation learning objectives are sufficient for control?
How can we best design representation learning objectives?
10 January 2022, by
BAIR blog
Understanding user interfaces with screen parsing
We introduce the problem of screen parsing, which we use to predict structured user interface models from visual information.
03 January 2022, by
ML@CMU
Bridge data: boosting generalization of robotic skills with cross-domain datasets
With our proposed dataset and multi-task, multi-domain learning approach, we have shown one potential avenue for making diverse datasets reusable in robotics.
30 December 2021, by
BAIR blog
Why generalization in RL is difficult: epistemic POMDPs and implicit partial observability
In this blog post, we will aim to explain why generalization in RL is fundamentally hard, even in theory.
21 December 2021, by
BAIR blog
Designs from data: offline black-box optimization via conservative training
In this post, we discuss offline model-based optimization and some recent advances in this area.
10 December 2021, by
BAIR blog
A first-principles theory of neural network generalization
Find out more about research trying to shed light on the workings of deep neural networks.
22 November 2021, by
BAIR blog
Compression, transduction, and creation: a unified framework for evaluating natural language generation
Our framework classifies language generation tasks into compression, transduction, and creation.
18 November 2021, by
ML@CMU
Making RL tractable by learning more informative reward functions: example-based control, meta-learning, and normalized maximum likelihood
This article presents MURAL, a method for learning uncertainty-aware rewards for RL.
15 November 2021, by
BAIR blog
PICO: Pragmatic compression for human-in-the-loop decision-making
In this post, we outline a pragmatic compression algorithm called PICO.
05 November 2021, by
BAIR blog
Unsolved ML safety problems
We provide a new roadmap for ML Safety and aim to refine the technical problems that the field needs to address.
26 October 2021, by
BAIR blog
Distilling neural networks into wavelet models using interpretations
We propose a method which distills information from a trained DNN into a wavelet transform.
18 October 2021, by
BAIR blog
What can I do here? Learning new skills by imagining visual affordances
Can we use an analogous strategy to a child learning in a robotic learning system?
30 September 2021, by
BAIR blog
The limitations of limited context for constituency parsing
We consider the representational power of two important frameworks for constituency parsing.
24 September 2021, by
ML@CMU
Strategic instrumental variable regression: recovering causal relationships from strategic responses
How can we infer causal relationships in data while employing a decision-making model?
08 September 2021, by
ML@CMU
Universal weakly supervised segmentation by pixel-to-segment contrastive learning
Can a machine learn from a few labeled pixels to predict every pixel in a new image?
17 August 2021, by
BAIR blog
A unifying, game-theoretic framework for imitation learning
In this post we explore imitation learning and consider online, offline, and interactive methods.
13 August 2021, by
ML@CMU
The surprising effectiveness of PPO in cooperative multi-agent games
A study of cooperative multi-agent tasks, in which a group of agents is trying to optimize a shared reward function.
06 August 2021, by
BAIR blog
