AGI & CoCoSci
837 items from yuzheshi/awesome-agi-cocosci ★398
-
Understanding Deep Architectures with Reasoning Layer proceedings.neurips.cc
NeurIPS'20, 2020. [All Versions].
-
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation proceedings.neurips.cc
NeurIPS'19, 2019. [All Versions].
-
PHYRE: A New Benchmark for Physical Reasoning proceedings.neurips.cc
NeurIPS'19, 2019. [All Versions]. A benchmark for AI physical reasoning.
-
Learning by Abstraction: The Neural State Machine proceedings.neurips.cc
NeurIPS'19, 2019. [All Versions].
-
Bayesian Model-Agnostic Meta-Learning proceedings.neurips.cc
NeurIPS'18, 2018. [All Versions]. A Bayesian account on MAML.
-
Learning to Infer Graphics Programs from Hand-Drawn Images proceedings.neurips.cc
NeurIPS'18, 2018. [All Versions]. The method learns a model that uses program synthesis techniques to recover a graphics program from drawing primitives. These programs have constructs like variable bindings, iterative loops, or simple kinds of conditionals. With a graphics…
-
Towards Understanding Learning Representations: To What Extent Do Different Neural Networks Learn the Same… proceedings.neurips.cc
NeurIPS'18, 2018. [All Versions]. Maching the learned pattern of neurons in different neural networks.
-
Emergence of Language with Multi-agent Games: Learning to Communicate with Sequences of Symbols proceedings.neurips.cc
NeurIPS'18, 2018. [All Versions].
-
Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning proceedings.neurips.cc
NeurIPS'15, 2015. [All Versions]. The original paper on empowerment as intrinsic motivation.
-
VISALOGY: Answering Visual Analogy Questions proceedings.neurips.cc
NeurIPS'15, 2015. [All Versions].
-
Practical Bayesian Optimization of Machine Learning Algorithms proceedings.neurips.cc
NeurIPS'12, 2012. [All Versions]. The use of machine learning algorithms frequently involves careful tuning of learning parameters and model hyperparameters. Unfortunately, this tuning is often a “black art” requiring expert experience, rules of thumb, or sometimes brute-force…
-
Testing a Bayesian Measure of Representativeness Using a Large Image Database proceedings.neurips.cc
NeurIPS'11, 2011. [All Versions].
-
Efficient Learning of Sparse Representations with an Energy-Based Model proceedings.neurips.cc
NeurIPS'06, 2006. [All Versions].
-
Intrinsically Motivated Reinforcement Learning proceedings.neurips.cc
NeurIPS'04, 2004. [All Versions]. A comprehensive review on intrinsic reward functions in classic reinforcement learning.
-
From Algorithmic to Subjective Randomness proceedings.neurips.cc
NeurIPS'03, 2003. [All Versions].
-
Hierarchical topic models and the nested Chinese restaurant process proceedings.neurips.cc
NeurIPS'03, 2003. [All Versions]. The original paper for nested Chinese restaurant process.
-
Rules and Similarity in Concept Learning proceedings.neurips.cc
NeurIPS'99, 1999. [All Versions]. [Preprint]. This paper argues that two apparently distinct modes of generalizing concepts - abstracting rules and computing similarity to exemplars - should both be seen as special cases of a more general Bayesian learning framework. Bayes…
-
Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables proceedings.mlr.press
ICML'19, 2019. [All Versions].
-
Analogies Explained: Towards Understanding Word Embeddings proceedings.mlr.press
ICML'19, 2019. [All Versions]. Explaining the analogy capability in word embeddings.
-
Machine theory of mind proceedings.mlr.press
ICML'18, 2018. [All Versions]. Theory of mind (ToM) broadly refers to humans’ ability to represent the mental states of others, including their desires, beliefs, and intentions. This work proposes a Theory of Mind neural network --- a ToMnet --- which uses meta-learning to…
-
Investigating Human Priors for Playing Video Games proceedings.mlr.press
ICML'18, 2018. [All Versions].
-
Curiosity-driven Exploration by Self-supervised Prediction proceedings.mlr.press
ICML'17, 2017. [All Versions]. The original paper on curiosity as intrinsic motivation.
-
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks proceedings.mlr.press
ICML'17, 2017. [All Versions]. [Post]. Chelsea Finn's original paper on Model-Agnostic Meta-Learning (MAML).
-
Constrained Policy Optimization proceedings.mlr.press
ICML'17, 2017. [All Versions]. The original paper on constrained reinforcement learning (safe reinforcement learning).
-
A Theory of Generative ConvNet proceedings.mlr.press
ICML'16, 2016. [All Versions]. The authors show that a generative random field model, which they call generative ConvNet, can be derived from the commonly used discriminative ConvNet, by assuming a ConvNet for multi-category classification and assuming one of the category is a…
-
Trust Region Policy Optimization proceedings.mlr.press
ICML'15, 2015. [All Versions]. The original paper introducing TRPO, a method for optimizing control policies, with guaranteed monotonic improvement.
-
Analogy-preserving Semantic Embedding for Visual Object Categorization proceedings.mlr.press
ICML'13, 2013. [All Versions]. The first application of analogy to machine learning.
-
On the Complexity of Bayesian Generalization proceedings.mlr.press
ICML'23, 2023. [All Versions]. [Project]. [Models]. This work examines concept generalization at a large scale in the natural visual spectrum. Established computational modes (i.e., rule-based or similarity-based) are primarily studied isolated, focusing on confined and…
-
PAL: Program-aided Language Models proceedings.mlr.press
ICML'23, 2023. [All Versions]. Paper presenting an approach that uses the LLM to read natural language problems and generate programs as the intermediate reasoning steps, but offloads the solution step to a runtime such as a Python interpreter. With PAL, decomposing the natural…
-
A Language for Counterfactual Generative Models proceedings.mlr.press
ICML'21, 2021. [All Versions]. [Project]. This paper presents Omega, a probabilistic programming language with support for counterfactual inference. This feature is accomplished by introducing a new operator to probabilistic programming akin to Pearl’s do.
-
AGENT: A Benchmark for Core Psychological Reasoning proceedings.mlr.press
ICML'21, 2021. [All Versions]. Inspired by cognitive development studies on intuitive psychology, this paper presents a benchmark consisting of a large dataset of procedurally generated 3D animations, AGENT (Action, Goal, Efficiency, coNstraint, uTility), structured around four…
-
TeachMyAgent: a Benchmark for Automatic Curriculum Learning in Deep RL proceedings.mlr.press
ICML'21, 2021. [All Versions]. [Project].
-
Inverse Constrained Reinforcement Learning proceedings.mlr.press
ICML'21, 2021. [All Versions].
-
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning proceedings.mlr.press
ICML'21, 2021. [All Versions]. [Code].
-
Latent Programmer: Discrete Latent Codes for Program Synthesis proceedings.mlr.press
ICML'21, 2021. [All Versions]. Paper introducing the Latent Programmer, a two-level program synthesis method that first predicts a discrete latent code from input/output examples, and then generates the program in the target language.
-
PClean: Bayesian Data Cleaning at Scale with Domain-Specific Probabilistic Programming proceedings.mlr.press
ICML'21, 2021. [All Versions]. This work presents PClean, a probabilistic programming language (PPL) for leveraging dataset-specific knowledge to automate Bayesian cleaning, automating Bayesian approaches given the diversity of real-world error patterns and the hardness of…
-
Latent Space Factorisation and Manipulation via Matrix Subspace Projection proceedings.mlr.press
ICML'20, 2020. [All Versions].
-
Functional neuroanatomy of intuitive physical inference pnas.org
Proceedings of the National Academy of Sciences, 2016. [All Versions]. A piece of evidence for the functional part of intuitive physics in human brain.
-
Bayesian modeling of human–AI complementarity pnas.org
Proceedings of the National Academy of Sciences, 2022. [All Versions]. A Bayesian framework for combining the predictions and different types of confidence scores from humans and machines.
-
Proceedings of the National Academy of Sciences, 2021. [All Versions].
-
Finding scientific topics pnas.org
Proceedings of the National Academy of Sciences, 2004. [All Versions]. A first step in identifying the content of a document is determining which topics that document addresses. This paper describes a generative model for documents, in which each document is generated by…
-
Slowed Canonical Progress in Large Fields of Science pnas.org
Proceedings of the National Academy of Sciences, 2021. [All Verisions]. An analysis of why too many papers published each year in a field can lead to stagnation rather than advance.
-
Scaling up psychology via Scientific Regret Minimization pnas.org
Proceedings of the National Academy of Sciences, 2020. [All Versions]. The statistical and ecological basis for scaling up behavioral studies.
-
Meta-assessment of Bias in Science pnas.org
Proceedings of the National Academy of Sciences, 2017. [All Verisions]. An analysis of bias patterns and risk factors in science.
-
Understanding the role of Individual Units in a Deep Neural Network pnas.org
Proceedings of the National Academy of Sciences, 2020. [All Versions]. David Bau's review on network dissection for discriminative and generative models.
-
Rapid trail-and-error learning with simulation supports flexible tool use and physical reasoning. pnas.org
Proceedings of the National Academy of Sciences, 2020. [All Versions]. [Project]. [Appendix]. Many animals, and an increasing number of artificial agents, display sophisticated capabilities to perceive and manipulate objects. But human beings remain distinctive in their…
-
Unsupervised learning by competing hidden units pnas.org
Proceedings of the National Academy of Sciences, 2019. [All Versions].
-
Emergence of analogy from relation learning pnas.org
Proceedings of the National Academy of Sciences, 2019. [All Versions]. Analogy feature in language models.
-
Simulation as an engine of physical scene understanding pnas.org
Proceedings of the National Academy of Sciences, 2013. [All Versions]. [Appendix]. The first attempt to computationally simulate intuitive physics.
-
Communicating artificial neural networks develop efficient color-naming systems pnas.org
Proceedings of the National Academy of Sciences, 2021. [All Versions]. Simulating the emergence of code as the communication bottleneck in color learning task.
- next page of items loading…