• Publications
  • Influence
End-To-End Memory Networks
TLDR
A neural network with a recurrent attention model over a possibly large external memory that is trained end-to-end, and hence requires significantly less supervision during training, making it more generally applicable in realistic settings.
Learning Multiagent Communication with Backpropagation
TLDR
A simple neural model is explored, called CommNet, that uses continuous communication for fully cooperative tasks and the ability of the agents to learn to communicate amongst themselves is demonstrated, yielding improved performance over non-communicative agents and baselines.
Training Convolutional Networks with Noisy Labels
TLDR
An extra noise layer is introduced into the network which adapts the network outputs to match the noisy label distribution and can be estimated as part of the training process and involve simple modifications to current training infrastructures for deep networks.
Simple Baseline for Visual Question Answering
TLDR
A very simple bag-of-words baseline for visual question answering that concatenates the word features from the question and CNN features fromThe image to predict the answer.
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks
TLDR
This paper presents Individualized Controlled Continuous Communication Model (IC3Net) which has better training efficiency than simple continuous communication model, and can be applied to semi-cooperative and competitive settings along with the cooperative settings.
Learning from Noisy Labels with Deep Neural Networks
TLDR
A novel way of modifying deep learning models so they can be effectively trained on data with high level of label noise is proposed, and it is shown that random images without labels can improve the classification performance.
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play
TLDR
This work describes a simple scheme that allows an agent to learn about its environment in an unsupervised manner, and focuses on two kinds of environments: (nearly) reversible environments and environments that can be reset.
Adaptive Attention Span in Transformers
We propose a novel self-attention mechanism that can learn its optimal attention span. This allows us to extend significantly the maximum context size used in Transformer, while maintaining control
MazeBase: A Sandbox for Learning from Games
TLDR
MazeBase is introduced, an environment for simple 2D games, designed as a sandbox for machine learning approaches to reasoning and planning, and models trained on the MazeBase version can be directly applied to StarCraft, where they consistently beat the in-game AI.
Hash Layers For Large Sparse Models
TLDR
This work modify the feedforward layer to hash to different sets of weights depending on the current token, over all tokens in the sequence, and shows that this procedure either outperforms or is competitive with learning-to-route mixture-of-expert methods, while requiring no routing parameters or extra terms in the objective function.
...
...