Search Results for author:
Found 9 papers, 8 papers with code
Prover-Verifier Games improve legibility of LLM outputs
One way to increase confidence in the outputs of Large Language Models (LLMs) is to support them with reasoning that is clear and easy to check -- a property we call legibility.
Grokking: Generalization Beyond Overfitting on Small Algorithmic Datasets
In this paper we propose to study generalization of neural networks on small algorithmically generated datasets.
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
Exploration by Random Network Distillation
In particular we establish state of the art performance on Montezuma's Revenge, a game famously difficult for deep reinforcement learning methods.
Large-Scale Study of Curiosity-Driven Learning
However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent.
Ranked #14 on
Atari Games
on Atari 2600 Montezuma's Revenge
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.
On the Quantitative Analysis of Decoder-Based Generative Models
The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities.
Importance Weighted Autoencoders
The variational autoencoder (VAE; Kingma, Welling (2014)) is a recently proposed generative model pairing a top-down generative network with a bottom-up recognition network which approximates posterior inference.
Accurate and Conservative Estimates of MRF Log-likelihood using Reverse Annealing
Markov random fields (MRFs) are difficult to evaluate as generative models because computing the test log-probabilities requires the intractable partition function.
