Search Results for author:
Found 73 papers, 49 papers with code
Conditional Augmentation for Generative Modeling
We present conditional augmentation (CondAugment), a simple and powerful method of regularizing generative models.
OpenAI o1 System Card
The o1 model series is trained with large-scale reinforcement learning to reason using chain of thought.
GPT-4o System Card
We also include third-party assessments on dangerous capabilities, as well as discussion of potential societal impacts of GPT-4o's text and vision capabilities.
Ranked #1 on
Visual Question Answering (VQA)
on VLM2-Bench
Scaling and evaluating sparse autoencoders
Using these techniques, we find clean scaling laws with respect to autoencoder size and sparsity.
Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervision
Widely used alignment techniques, such as reinforcement learning from human feedback (RLHF), rely on the ability of humans to supervise model behavior - for example, to evaluate whether a model faithfully followed instructions or generated safe outputs.
Let's Verify Step by Step
We conduct our own investigation, finding that process supervision significantly outperforms outcome supervision for training models to solve problems from the challenging MATH dataset.
Ranked #1 on
Math Word Problem Solving
on MATH minival
(using extra training data)
GPT-4 Technical Report
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs.
Ranked #1 on
Question Answering
on PeerQA
Consistency Models
Through extensive experiments, we demonstrate that they outperform existing distillation techniques for diffusion models in one- and few-step sampling, achieving the new state-of-the-art FID of 3. 55 on CIFAR-10 and 6. 20 on ImageNet 64x64 for one-step generation.
Ranked #23 on
Image Generation
on ImageNet 64x64
Robust Speech Recognition via Large-Scale Weak Supervision
We study the capabilities of speech processing systems trained simply to predict large amounts of transcripts of audio on the internet.
Ranked #1 on
Zero-Shot Audio Retrieval
on VocSim
Formal Mathematics Statement Curriculum Learning
We explore the use of expert iteration in the context of language modeling applied to formal mathematics.
Ranked #12 on
Automated Theorem Proving
on miniF2F-test
(using extra training data)
GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models
Diffusion models have recently been shown to generate high-quality synthetic images, especially when paired with a guidance technique to trade off diversity for fidelity.
Ranked #32 on
Text-to-Image Generation
on MS COCO
(using extra training data)
Unsupervised Neural Machine Translation with Generative Language Models Only
We show how to derive state-of-the-art unsupervised neural machine translation systems from generatively pre-trained language models.
Evaluating Large Language Models Trained on Code
We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities.
Ranked #1 on
Multi-task Language Understanding
on BBH-alg
Learning Transferable Visual Models From Natural Language Supervision
State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories.
Ranked #1 on
Zero-Shot Learning
on COCO-MLT
(using extra training data)
Zero-Shot Text-to-Image Generation
Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset.
Generative Language Modeling for Automated Theorem Proving
We explore the application of transformer-based language models to automated theorem proving.
Ranked #1 on
Automated Theorem Proving
on Metamath set.mm
Generative Pretraining from Pixels
Inspired by progress in unsupervised representation learning for natural language, we examine whether similar models can learn useful representations for images.
Ranked #14 on
Image Classification
on STL-10
(using extra training data)
Representation Learning
Self-Supervised Image Classification
Language Models are Few-Shot Learners
By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
Ranked #1 on
Question Answering
on CoQA
(Overall metric)
Jukebox: A Generative Model for Music
We introduce Jukebox, a model that generates music with singing in the raw audio domain.
Dota 2 with Large Scale Deep Reinforcement Learning
On April 13th, 2019, OpenAI Five became the first AI system to defeat the world champions at an esports game.
Deep Double Descent: Where Bigger Models and More Data Hurt
We show that a variety of modern deep learning tasks exhibit a "double-descent" phenomenon where, as we increase model size, performance first gets worse and then gets better.
Generating Long Sequences with Sparse Transformers
Transformers are powerful sequence models, but require time and memory that grows quadratically with the sequence length.
Language Models are Unsupervised Multitask Learners
Natural language processing tasks, such as question answering, machine translation, reading comprehension, and summarization, are typically approached with supervised learning on taskspecific datasets.
Ranked #1 on
Language Modelling
on enwik8
(using extra training data)
The Importance of Sampling inMeta-Reinforcement Learning
Results are presented on a new environment we call `Krazy World': a difficult high-dimensional gridworld which is designed to highlight the importance of correctly differentiating through sampling distributions in meta-reinforcement learning.
FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models
The result is a continuous-time invertible generative model with unbiased density estimation and one-pass sampling, while allowing unrestricted neural network architectures.
Ranked #1 on
Density Estimation
on UCI MINIBOONE
Improving Language Understanding by Generative Pre-Training
We demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task.
Ranked #3 on
Natural Language Inference
on SciTail
GamePad: A Learning Environment for Theorem Proving
In this paper, we introduce a system called GamePad that can be used to explore the application of machine learning methods to theorem proving in the Coq proof assistant.
Some Considerations on Learning to Explore via Meta-Reinforcement Learning
We consider the problem of exploration in meta reinforcement learning.
Generative Models for Alignment and Data Efficiency in Language
We examine how learning from unaligned data can improve both the data efficiency of supervised tasks as well as enable alignments without any supervision.
Emergent Complexity via Multi-Agent Competition
In this paper, we point out that a competitive multi-agent environment trained with self-play can produce behaviors that are far more complex than the environment itself.
Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
Ability to continuously learn and adapt from limited experience in nonstationary environments is an important milestone on the path towards general intelligence.
An online sequence-to-sequence model for noisy speech recognition
This is because the models require that the entirety of the input sequence be available at the beginning of inference, an assumption that is not valid for instantaneous speech recognition.
Learning to Generate Reviews and Discovering Sentiment
We explore the properties of byte-level recurrent language models.
Ranked #9 on
Subjectivity Analysis
on SUBJ
One-Shot Imitation Learning
A neural net is trained that takes as input one demonstration and the current state (which initially is the initial state of the other demonstration of the pair), and outputs an action with the goal that the resulting sequence of states and actions matches as closely as possible with the second demonstration.
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
We explore the use of Evolution Strategies (ES), a class of black box optimization algorithms, as an alternative to popular MDP-based RL techniques such as Q-learning and Policy Gradients.
Ranked #1 on
Atari Games
on Atari 2600 Pong
Third-Person Imitation Learning
A key difficulty in reinforcement learning is specifying a reward function for the agent to optimize.
An Online Sequence-to-Sequence Model Using Partial Conditioning
However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output sequences.
Improved Variational Inference with Inverse Autoregressive Flow
The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.
RL$^2$: Fast Reinforcement Learning via Slow Reinforcement Learning
The activations of the RNN store the state of the "fast" RL algorithm on the current (previously unseen) MDP.
Variational Lossy Autoencoder
Representation learning seeks to expose certain aspects of observed data in a learned representation that's amenable to downstream tasks like classification.
Extensions and Limitations of the Neural GPU
We find that these techniques increase the set of algorithmic problems that can be solved by the Neural GPU: we have been able to learn to perform all the arithmetic operations (and generalize to arbitrarily long numbers) when the arguments are given in the decimal representation (which, surprisingly, has not been possible before).
Learning Online Alignments with Continuous Rewards Policy Gradient
Though capable and easy to use, they require that the entirety of the input sequence is available at the beginning of inference, an assumption that is not valid for instantaneous translation and speech recognition.
Improving Variational Inference with Inverse Autoregressive Flow
The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables.
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
This paper describes InfoGAN, an information-theoretic extension to the Generative Adversarial Network that is able to learn disentangled representations in a completely unsupervised manner.
Ranked #3 on
Image Generation
on Stanford Cars
TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
TensorFlow is an interface for expressing machine learning algorithms, and an implementation for executing such algorithms.
Continuous Deep Q-Learning with Model-based Acceleration
In this paper, we explore algorithms and representations to reduce the sample complexity of deep reinforcement learning for continuous control tasks.
Neural GPUs Learn Algorithms
Unlike the NTM, the Neural GPU is highly parallel which makes it easier to train and efficient to run.
Adding Gradient Noise Improves Learning for Very Deep Networks
This success is partially attributed to architectural innovations such as convolutional and long short-term memory networks.
Towards Principled Unsupervised Learning
Supervised learning is successful because it can be solved by the minimization of the training error cost function.
Neural Random-Access Machines
In this paper, we propose and investigate a new neural network architecture called Neural Random Access Machine.
Multi-task Sequence to Sequence Learning
This paper examines three multi-task learning (MTL) settings for sequence to sequence models: (a) the oneto-many setting - where the encoder is shared between several tasks such as machine translation and syntactic parsing, (b) the many-to-one setting - useful when only the decoder can be shared, as in the case of translation and image caption generation, and (c) the many-to-many setting - where multiple encoders and decoders are shared, which is the case with unsupervised objectives and translation.
Neural Programmer: Inducing Latent Programs with Gradient Descent
In this work, we propose Neural Programmer, an end-to-end differentiable neural network augmented with a small set of basic arithmetic and logic operations.
MuProp: Unbiased Backpropagation for Stochastic Neural Networks
Deep neural networks are powerful parametric models that can be trained efficiently using the backpropagation algorithm.
A Neural Transducer
However, they are unsuitable for tasks that require incremental predictions to be made as more data arrives or tasks that have long input sequences and output sequences.
Reinforcement Learning Neural Turing Machines - Revised
The capabilities of a model can be extended by providing it with proper Interfaces that interact with the world.
Grammar as a Foreign Language
Syntactic constituency parsing is a fundamental problem in natural language processing and has been the subject of intensive research and engineering for decades.
Ranked #25 on
Constituency Parsing
on Penn Treebank
Move Evaluation in Go Using Deep Convolutional Neural Networks
The game of Go is more challenging than other board games, due to the difficulty of constructing a position or move evaluation function.
Addressing the Rare Word Problem in Neural Machine Translation
Our experiments on the WMT14 English to French translation task show that this method provides a substantial improvement of up to 2. 8 BLEU points over an equivalent NMT system that does not use this technique.
Ranked #41 on
Machine Translation
on WMT2014 English-French
Learning to Execute
Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train.
Sequence to Sequence Learning with Neural Networks
Our method uses a multilayered Long Short-Term Memory (LSTM) to map the input sequence to a vector of a fixed dimensionality, and then another deep LSTM to decode the target sequence from the vector.
Ranked #4 on
Traffic Prediction
on PeMS-M
(using extra training data)
Recurrent Neural Network Regularization
We present a simple regularization technique for Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) units.
Ranked #36 on
Language Modelling
on Penn Treebank (Word Level)
Dropout: A Simple Way to Prevent Neural Networks from Overfitting
The key idea is to randomly drop units (along with their connections) from the neural network during training.
Intriguing properties of neural networks
Deep neural networks are highly expressive models that have recently achieved state of the art performance on speech and visual recognition tasks.
Learning Factored Representations in a Deep Mixture of Experts
In addition, we see that the different combinations are in use when the model is applied to a dataset of speech monophones.
Distributed Representations of Words and Phrases and their Compositionality
Motivated by this example, we present a simple method for finding phrases in text, and show that learning good vector representations for millions of phrases is possible.
Exploiting Similarities among Languages for Machine Translation
Dictionaries and phrase tables are the basis of modern statistical machine translation systems.
On the importance of initialization and momentum in deep learning
Deep and recurrent neural networks (DNNs and RNNs respectively) are powerful models that were considered to be almost impossible to train using stochastic gradient descent with momentum.
Cardinality Restricted Boltzmann Machines
The Restricted Boltzmann Machine (RBM) is a popular density model that is also good for extracting features.
ImageNet Classification with Deep Convolutional Neural Networks
We trained a large, deep convolutional neural network to classify the 1. 3 million high-resolution images in the LSVRC-2010 ImageNet training set into the 1000 different classes.
Ranked #4 on
Graph Classification
on HIV-fMRI-77
Improving neural networks by preventing co-adaptation of feature detectors
When a large feedforward neural network is trained on a small training set, it typically performs poorly on held-out test data.
Ranked #236 on
Image Classification
on CIFAR-10
Modelling Relational Data using Bayesian Clustered Tensor Factorization
We consider the problem of learning probabilistic models for complex relational structures between various types of objects.
Using matrices to model symbolic relationship
We describe a way of learning matrix representations of objects and relationships.
The Recurrent Temporal Restricted Boltzmann Machine
The Temporal Restricted Boltzmann Machine (TRBM) is a probabilistic model for sequences that is able to successfully model (i. e., generate nice-looking samples of) several very high dimensional sequences, such as motion capture data and the pixels of low resolution videos of balls bouncing in a box.
