User profiles for Zeming Lin
Zeming LinNew York University Verified email at nyu.edu Cited by 70355 |
Episodic exploration for deep deterministic policies: An application to starcraft micromanagement tasks
We consider scenarios from the real-time strategy game StarCraft as new benchmarks for
reinforcement learning algorithms. We propose micromanagement tasks, which present the …
reinforcement learning algorithms. We propose micromanagement tasks, which present the …
Automatic differentiation in pytorch
…, S Chintala, G Chanan, E Yang, Z DeVito, Z Lin… - 2017 - openreview.net
In this article, we describe an automatic differentiation module of PyTorch — a library designed
to enable rapid research on machine learning models. It builds upon a few projects, most …
to enable rapid research on machine learning models. It builds upon a few projects, most …
Pytorch: An imperative style, high-performance deep learning library
…, G Chanan, T Killeen, Z Lin…�- Advances in neural�…, 2019 - proceedings.neurips.cc
Deep learning frameworks have often focused on either usability or speed, but not both.
PyTorch is a machine learning library that shows that these two goals are in fact compatible: it …
PyTorch is a machine learning library that shows that these two goals are in fact compatible: it …
Intrinsic motivation and automatic curricula via asymmetric self-play
We describe a simple scheme that allows an agent to learn about its environment in an
unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against …
unsupervised manner. Our scheme pits two versions of the same agent, Alice and Bob, against …
Evolutionary-scale prediction of atomic-level protein structure with a language model
Recent advances in machine learning have leveraged evolutionary information in multiple
sequence alignments to predict protein structure. We demonstrate direct inference of full …
sequence alignments to predict protein structure. We demonstrate direct inference of full …
[PDF][PDF] Language models of protein sequences at the scale of evolution enable accurate structure prediction
Large language models have recently been shown to develop emergent capabilities with
scale, going beyond simple pattern matching to perform higher level reasoning and generate …
scale, going beyond simple pattern matching to perform higher level reasoning and generate …
Stardata: A starcraft ai research dataset
We release a dataset of 65646 StarCraft replays that contains 1535 million frames and 496
million player actions. We provide full game state data along with the original replays that can …
million player actions. We provide full game state data along with the original replays that can …
Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences
In the field of artificial intelligence, a combination of scale in data and model capacity
enabled by unsupervised learning has led to major advances in representation learning and …
enabled by unsupervised learning has led to major advances in representation learning and …
Learning inverse folding from millions of predicted structures
We consider the problem of predicting a protein sequence from its backbone atom coordinates.
Machine learning approaches to this problem to date have been limited by the number of …
Machine learning approaches to this problem to date have been limited by the number of …
Simulating 500 million years of evolution with a language model
More than three billion years of evolution have produced an image of biology encoded into
the space of natural proteins. Here we show that language models trained on tokens …
the space of natural proteins. Here we show that language models trained on tokens …