AI
Artificial intelligence: machine learning, neural networks, large language models, deep learning, AI research, and AI tools.
-
Watch-And-Help: A Challenge for Social Perception and Human-AI Collaboration openreview.net
ICLR'21, 2021. [All Versions].
-
Learning to Perform Physics Experiments via Deep Reinforcement Learning openreview.net
ICLR'17, 2017. [All Versions].
-
NBDT: Neural-Backed Decision Trees openreview.net
ICLR'21, 2021. [All Versions]. [Code]. Machine learning applications such as finance and medicine demand accurate and justifiable predictions, barring most deep learning methods from use. In response, previous work combines decision trees with deep learning, yielding models…
-
HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making openreview.net
AAMAS'26, 2026. [All Versions]. Benchmarks are crucial for assessing multi-agent reinforcement learning (MARL) algorithms. While StarCraft II-related environments have driven significant advances in MARL, existing benchmarks like SMAC focus primarily on micromanagement…
-
Meta-Q-Learning openreview.net
ICLR'20, 2020. [All Versions]. The milestone paper on context Meta-RL.
-
Physion: Evaluating Physical Prediction from Vision in Humans and Machines openreview.net
NeurIPS'21, 2021. [All Versions].
-
Metacontrol for Adaptive Imagination-Based Optimization openreview.net
ICLR'17, 2017. [All Versions].
-
Hierarchically Encapsulated Representation for Protocol Design in Self-Driving Labs openreview.net
ICLR'25, 2025. [All Versions]. [Project]. Self-driving laboratories have begun to replace human experimenters in performing single experimental skills or predetermined experimental protocols. However, as the pace of idea iteration in scientific research has been intensified by…
-
Solving Compositional Reinforcement Learning Problems via Task Reduction openreview.net
ICLR'21, 2021. [All Versions].
-
Visual Programming: Compositional Visual Reasoning Without Training openaccess.thecvf.com
CVPR'23, 2023. [All Versions]. VISPROG, a neuro-symbolic approach to solving complex and compositional visual tasks given natural language instructions, using the in-context learning ability of large language models to generate python-like modular programs, which are then…
-
Rational Use of Cognitive Resources: Levels of Analysis Between the Computational and the Algorithmic onlinelibrary.wiley.com
Topics in Cognitive Science, 2015. [All Versions]. An earlier version of the paper above.
-
The AHA! Experience: Creativity Through Emergent Binding in Neural Networks onlinelibrary.wiley.com
Cognitive Science, 2012. [All Versions].
-
What Is the Model in Model-Based Planning? onlinelibrary.wiley.com
Cognitive Science, 2021. [All Versions].
-
PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception ojs.aaai.org
AAAI'21, 2021. [All Versions]. [Project].
-
Theory-Based Causal Transfer: Integrating Instance-Level Induction and Abstract-Level Structure Learning ojs.aaai.org
AAAI'20, 2020. [All Versions]. A computatinoal account on causal transfer.
-
Abduction-Based Explanations for Machine Learning Models ojs.aaai.org
AAAI'19, 2019. [All Versions]. The growing range of applications of Machine Learning (ML) in a multitude of settings motivates the ability of computing small explanations for predictions made. Small explanations are generally accepted as easier for human decision makers to…
-
Quantifying artificial intelligence through algorithmic generalization nature.com
Nature Machine Intelligence, 2025. [All Versions]. The rapid development of artificial intelligence (AI) systems has created an urgent need for their scientific quantification. While their fluency across a variety of domains is impressive, AI systems fall short on tests…
-
The future of open human feedback nature.com
Nature Machine Intelligence, 2025. [All Versions]. Human feedback on conversations with language models is central to how these systems learn about the world, improve their capabilities and are steered towards desirable and safe behaviours. However, this feedback is mostly…
-
Embodied large language models enable robots to complete complex tasks in unpredictable environments nature.com
Nature Machine Intelligence, 2025. [All Versions]. Completing complex tasks in unpredictable settings challenges robotic systems, requiring a step change in machine intelligence. Sensorimotor abilities are considered integral to human intelligence. Thus, biologically inspired…
-
Large language models for scientific discovery in molecular property prediction nature.com
Nature Machine Intelligence, 2025. [All Versions]. Large language models (LLMs) are a form of artificial intelligence system encapsulating vast knowledge in the form of natural language. These systems are adept at numerous complex tasks including creative writing, storytelling…
-
Augmenting large language models with chemistry tools nature.com
Nature Machine Intelligence, 2023. [All Versions]. [Preprint]. This paper introduces ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery and materials design. By integrating 18 expert-designed tools and using GPT-4 as the LLM…
-
Explaining machine learning models with interactive natural language conversations using TalkToModel nature.com
Nature Machine Intelligence, 2023. [All Versions]. Practitioners increasingly use machine learning (ML) models, yet models have become more complex and harder to understand. To understand complex models, researchers have proposed techniques to explain model predictions…
-
Phy-Q as a measure for physical reasoning intelligence nature.com
Nature Machine Intelligence, 2023. [NMI Challenge]. An interactive benchmark for AI physical reasoning.
-
An intelligent guided troubleshooting method for aircraft based on HybirdRAG nature.com
Scientific Reports, 2025. [All Versions]. To enhance aircraft fault diagnosis efficiency, this paper proposes HybridRAG, an intelligent-guided troubleshooting framework that integrates knowledge graphs and large language models (LLMs). Unlike conventional retrieval-augmented…
-
Dual retrieving and ranking medical large language model with retrieval augmented generation nature.com
Scientific Reports, 2025. [All Versions]. Recent advancements in large language models (LLMs) have significantly enhanced text generation across various sectors; however, their medical application faces critical challenges regarding both accuracy and real-time responsiveness…
-
Meta-analysis of the functional neuroimaging literature with probabilistic logic programming nature.com
Scientific Reports, 2022. [All Versions]. Inferring reliable brain-behavior associations requires synthesizing evidence from thousands of functional neuroimaging studies through meta-analysis. However, existing meta-analysis tools are limited to investigating simple…
-
Design of metalloproteins and novel protein folds using variational autoencoders nature.com
Scientific Reports, 2018. [All Versions]. The design of novel proteins has many applications but remains an attritional process with success in isolated cases. Meanwhile, deep learning technologies have exploded in popularity in recent years and are increasingly applicable to…
-
Using human brain activity to guide machine learning nature.com
Scientific Report, 2018. [All Versions].
-
Shared computational principles for language processing in humans and deep language models nature.com
Nature Neuroscience, 2022. [All Versions].
-
Nature Medicine, 2019. [All Versions]. The microscopic assessment of tissue samples is instrumental for the diagnosis and staging of cancer, and thus guides therapy. However, these assessments demonstrate considerable variability and many regions of the world lack access to…
-
Towards end-to-end automation of AI research nature.com
Nature, 2026. [All Versions]. The automation of science is a long-standing ambition in artificial intelligence (AI) research. Although the community has made substantial progress in automating individual components of the scientific process, a system that autonomously navigates…
-
The Virtual Lab of AI agents designs new SARS-CoV-2 nanobodies nature.com
Nature, 2025. [All Versions]. Science frequently benefits from teams of interdisciplinary researchers, but many scientists do not have easy access to experts from multiple fields. Although large language models (LLMs) have shown an impressive ability to aid researchers across…
-
Mathematical discoveries from program search with large language models nature.com
Nature, 2024. [All Versions]. Large language models (LLMs) have demonstrated tremendous capabilities in solving complex tasks, from quantitative reasoning to understanding natural language. However, LLMs sometimes suffer from confabulations (or hallucinations), which can result…
-
Autonomous chemical research with large language models nature.com
Nature, 2023. [All Versions]. An artificial intelligence system driven by GPT-4 that autonomously designs, plans and performs complex experiments by incorporating large language models empowered by tools such as internet and documentation search, code execution and experimental…
-
An autonomous laboratory for the accelerated synthesis of novel materials nature.com
Nature, 2023. [All Versions]. This paper introduces the A-Lab, an autonomous laboratory for the solid-state synthesis of inorganic powders. This platform uses computations, historical data from the literature, machine learning (ML) and active learning to plan and interpret the…
-
Scientific discovery in the age of artificial intelligence nature.com
Nature, 2023. [All Versions]. A review article that examines breakthroughs over the past decade that include self-supervised learning, which allows models to be trained on vast amounts of unlabelled data, and geometric deep learning, which leverages knowledge about the…
-
Accurate medium-range global weather forecasting with 3D neural networks nature.com
Nature, 2023. [All Versions]. This paer introduces an artificial-intelligence-based method for accurate, medium-range global weather forecasting. It shows that three-dimensional deep networks equipped with Earth-specific priors are effective at dealing with complex patterns in…
-
Human–machine collaboration for improving semiconductor process development nature.com
Nature, 2023. [All Versions]. [Nature News]. This work studies Bayesian optimization algorithms to investigate how artificial intelligence (AI) might decrease the cost of developing complex semiconductor chip processes. In particular, this work create a controlled virtual…
-
Building machines that learn and think with people nature.com
Nature Human Behavior, 2024. [All Versions]. [Preprint]. This perspective shows how the science of collaborative cognition can be put to work to engineer systems that really can be called ‘thought partners’, systems built to meet humans' expectations and complement humans…
-
Intuitive physics learning in a deep-learning model inspired by developmental psychology nature.com
Nature Human Behavior, 2022. [All Versions]. A machine-learning dataset designed to evaluate conceptual understanding of intuitive physics, adopting the violation-of-expectation (VoE) paradigm from developmental psychology; a deep-learning system that learns intuitive physics…
-
Nature Communications, 2025. [All Versions]. [Project]. Functional proteomics provides critical insights into cancer mechanisms, facilitating the discovery of novel biomarkers and therapeutic targets. The authors have developed a comprehensive cancer functional proteomics…
-
Nature Communications, 2024. [All Versions]. The material acceleration platform, empowered by robotics and artificial intelligence, is a transformative approach for expediting material discovery processes across diverse domains. However, the development of an operating system…
-
A human-machine interface for automatic exploration of chemical reaction networks nature.com
Nature Communications, 2024. [All Versions]. Autonomous reaction network exploration algorithms offer a systematic approach to explore mechanisms of complex chemical processes. However, the resulting reaction networks are so vast that an exploration of all potentially…
-
Structured information extraction from scientific text with large language models nature.com
Nature Communications, 2024. [All Versions]. This paper presents a simple approach to joint named entity recognition and relation extraction and demonstrate how pretrained large language models can be fine-tuned to extract useful records of complex scientific knowledge. The…
-
Nature Communications, 2023. [All Versions]. This paper introduces a transformer model for automated synthesis protocol analysis in catalyst discovery, exemplified using single-atom heterogeneous catalysts (SACs), a rapidly expanding catalyst family. The model adeptly converts…
-
Nature Communications, 2023. [All Versions]. [Project]. Advances in machine learning (ML) and automated experimentation are poised to vastly accelerate research in polymer science. Data representation is a critical aspect for enabling ML integration in research workflows, yet…
-
Synthesizing theories of human language with Bayesian program induction nature.com
Nature Communications, 2022. [All Versions]. Automated, data-driven construction and evaluation of scientific models and theories is a long-standing challenge in artificial intelligence. This work presents a framework for algorithmically synthesizing models of a basic part of…
-
Single-atom alloy catalysts designed by first-principles calculations and artificial intelligence nature.com
Nature Communications, 2021. [All Versions]. This paper addresses the problem of new Single-atom-alloy catalysts (SAACs) discovery by applying a compressed-sensing data-analytics approach parameterized with density-functional inputs.
-
Probabilistic machine learning and artificial intelligence nature.com
Nature, 2015. [All Versions]. Probabilistic modelling provides a framework for understanding what learning is, and has therefore emerged as one of the principal theoretical and practical approaches for designing machines that learn from data acquired through experience. The…
-
Functional genomic hypothesis generation and experimentation by a robot scientist nature.com
Nature, 2004. [All Versions]. This paper describes a physically implemented robotic system that applies techniques from artificial intelligence to carry out cycles of scientific experimentation. The system automatically originates hypotheses to explain observations, devises…
- next page of items loading…
