- Nobel Turing Challenge: creating the engine for scientific discovery
- A Computational Inflection for Scientific Discovery
- The Automated AI-driven Future of Scientific Discovery
- Scientific discovery in the age of artificial intelligence
- Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
- Amplify scientific discovery with artificial intelligence
- Agents of Exploration and Discovery
- On scientific understanding with artificial intelligence
- Towards Robot Scientists for autonomous scientific discovery
- Artificial intelligence: A powerful paradigm for scientific research
- The Future of Fundamental Science Led by Generative Closed-Loop Artificial Intelligence
- Functional genomic hypothesis generation and experimentation by a robot scientist
- Emergent autonomous scientific research capabilities of large language models
- Combining data and theory for derivable scientific discovery with AI-Descartes
- NIMS-OS: an automation software to implement a closed loop between artificial intelligence and robotic experiments in materials science
- Automation isn't automatic
- Towards robotic laboratory automation Plug & Play: The “LAPP” framework
- Self-Driving Laboratories: A Paradigm Shift in Nanomedicine Development
- Autonomous Chemical Experiments: Challenges and Perspectives on Establishing a Self-Driving Lab
- Errors are Useful Prompts: Instruction Guided Task Programming with Verifier-Assisted Iterative Prompting
- Indicators for the use of robotic labs in basic biomedical research: a literature analysis
- Will AI write scientific papers in the future?
- Scientific Process Automation andWorkflow Management
- Automated Research Workflows for Accelerated Discovery
- FAIR Computational Workflows
- Exploring the Role of Machine Learning in Scientific Workflows: Opportunities and Challenges
- Scientific workflow: a survey and research directions
- Scientific Workflows: Past, Present and Future
- Pegasus, a workflow management system for science automation
- Scientific Workflow Management and the Kepler System
- The role of machine learning in scientific workflows
- Physics-informed learning of governing equations from scarce data
- Physics-Informed Machine Learning: A Survey on Problems, Methods and Applications
- Scientific Machine Learning through Physics-Informed Neural Networks: Where we are and What's next
- Scientific Machine Learning
- Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems
- Universal Differential Equations for Scientific Machine Learning
- Partial Differential Equations Meet Deep Neural Networks: A Survey
- When Physics Meets Machine Learning: A Survey of Physics-Informed Machine Learning
- PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
- Three Ways to Solve Partial Differential Equations with Neural Networks — A Review
- Gold-Standard Solutions to the Schrödinger Equation Using Deep Learning: How Much Physics Do We Need?
- Physics-informed machine learning
- Integrating Physics-Based Modeling With Machine Learning: A Survey
- Scientific intuition inspired by machine learning generated hypotheses
- Dendral: a case study of the first expert system for scientific hypothesis formation
- Digital Discovery of 100 diverse Quantum Experiments with PyTheus
- Automated discovery of fundamental variables hidden in experimental data
- AI Poincar´e: Machine Learning Conservation Laws from Trajectories
- Transformational machine learning: Learning how to learn from many related scientific problems
- Automated Scientific Discovery: From Equation Discovery to Autonomous Discovery Systems
- Interpretable Scientific Discovery with Symbolic Regression: A Review
- End-to-end symbolic regression with transformers
- Deep Symbolic Regression for Recurrent Sequences
- Deep symbolic regression: Recovering mathematical expressions from data via risk-seeking policy gradients
- Discovering Symbolic Models from Deep Learning with Inductive Biases
- AI Feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity
- AI Feynman: A physics-inspired method for symbolic regression
- Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discovery
- A Unified Framework for Deep Symbolic Regression
- Deep Learning and Symbolic Regression for Discovering Parametric Equations
- Augmenting Scientific Creativity with an Analogical Search Engine
- SOLVENT: A Mixed Initiative System for Finding Analogies between Research Papers
- Emergent Analogical Reasoning in Large Language Models
- Analogy in scientific discovery: The case of johannes kepler
- Taking the human out of the loop: A review of bayesian optimization
- Bayesian experimental design: A review
- ReAct: A Review Comment Dataset for Actionability (and more)
- NLPEER: A Unified Resource for the Computational Study of Peer Review
- Revise and Resubmit: An Intertextual Model of Text-based Collaboration in Peer Review
- Assisting Decision Making in Scholarly Peer Review: A Preference Learning Perspective
- PEERAssist: Leveraging on Paper-Review Interactions to Predict Peer Review Decisions
- A Dataset of Peer Reviews (PeerRead): Collection, Insights and NLP Applications
- Your paper has been accepted, rejected, or whatever: Automatic generation of scientific paper reviews
- AI-assisted peer review
- Generating Long and Informative Reviews with Aspect-Aware Coarse-to-Fine Decoding
- Is the future of peer review automated?
- Can We Automate Scientific Reviewing?
- KID-Review: Knowledge-Guided Scientific Review Generation with Oracle Pre-training
- Automated scholarly paper review: Possibility and challenges
- Automated scholarly paper review: Technologies and challenges
- Investigations on meta review generation from peer review texts leveraging relevant sub-tasks in the peer review pipeline
- Can a Machine Generate a Meta-Review? How Far Are We?
- Generating Summaries for Scientific Paper Review
- ReviewRobot: Explainable Paper Review Generation based on Knowledge Synthesis
- Artificial Intelligence, Automation and Peer Review
- Artificial intelligence technologies to support research assessment: A review
- Multi-task peer-review score prediction
- Deep Paper Gestalt
- Predicting article quality scores with machine learning: The UK Research Excellence Framework
- Can REF output quality scores be assigned by AI? Experimental evidence
- Novelpy: A Python package to measure novelty and disruptiveness of bibliometric and patent data
- Evaluating Research Novelty Detection: Counterfactual Approaches
- Measuring originality in science
- Citation Trajectory Prediction via Publication Influence Representation Using Temporal Knowledge Graph
- A review of scientific impact prediction: tasks, features and methods
- Predicting Long-Term Citations from Short-Term Linguistic Influence
- New trends in scientific knowledge graphs and research impact assessment
- Follow the Leader: Documents on the Leading Edge of Semantic Change Get More Citations
- SChuBERT: Scholarly Document Chunks with BERT-encoding boost Citation Count Prediction
- Predicting the Impact of Scientific Concepts Using Full-Text Features
- Challenges, Experiments, and Computational Solutions in Peer Review
- Attend to Your Review: A Deep Neural Network to Extract Aspects from Peer Reviews
- How Confident Was Your Reviewer? Estimating Reviewer Confidence from Peer Review Texts
- BetterPR: A Dataset for Estimating the Constructiveness of Peer Review Comments
- The lack of theory is painful: Modeling Harshness in Peer Review
- DISAPERE: A Dataset for Discourse Structure in Peer Review Discussions
- SCIFACT-OPEN: Towards open-domain scientific claim verification
- MULTIVERS: Improving scientific claim verification with weak supervision and full-document context
- Fact or Fiction: Verifying Scientific Claims
- Scientific Discourse Tagging for Evidence Extraction
- Galactica: A Large Language Model for Science
- Science in the age of large language models
- Towards Generalist Biomedical AI
- BioGPT: generative pre-trained transformer for biomedical text generation and mining
- A Survey of Large Language Models
- GatorTron: A Large Clinical Language Model to Unlock Patient Information from Unstructured Electronic Health Records
- Learning Foundation Language Models for Geoscience Knowledge Understanding and Utilization
- SCITUNE: Aligning Large Language Models with Scientific Multimodal Instructions
- On the Opportunities and Risks of Foundation Models
- IBM NASA Geospatial
- GPT-4 Technical Report
- AI-Based Language Models Powering Drug Discovery and Development
- Foundation models for generalist medical artificial intelligence
- PMC-LLaMA: Further Finetuning LLaMA on Medical Papers
- MoLFormer
- Emergent autonomous scientific research capabilities of large language models
- MatSciBERT: A materials domain language model for text mining and information extraction
- SPECTER: Document-level Representation Learning using Citation-informed Transformers
- Scientific Language Models for Biomedical Knowledge Base Completion: An Empirical Study
- SciRepEval: A Multi-Format Benchmark for Scientific Document Representations
- Do Large Language Models Understand Chemistry? A Conversation with ChatGPT
- What indeed can GPT models do in chemistry? A comprehensive benchmark on eight tasks
- Large Language Models, scientific knowledge and factuality
- An Empirical Study on Challenging Math Problem Solving with GPT-4
- Emergent Autonomous Scientific Research Capabilities of Large Language Models
- Capabilities of GPT-4 on Medical Challenge Problems
- MatSciBERT: A Materials Domain Language Model for Text Mining and Information Extraction
- Large Language Models as Master Key: Unlocking the Secrets of Materials Science with GPT
- The SciQA Scientific Question Answering Benchmark for Scholarly Knowledge
- QASA: Advanced Question Answering on Scientific Articles
- SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models
- A Dataset of Argumentative Dialogues on Scientific Papers
- The Semantic Scholar Open Data Platform
- What Can’t Large Language Models Do? The Future of AI-Assisted Academic Writing
- arXiVeri: Automatic table verification with GPT
- Comparing scientific abstracts generated by ChatGPT to real abstracts with detectors and blinded human reviewers
- Can GPT-3 write an academic paper on itself, with minimal human input?
- Extraction of Formulaic Expressions from Scientific Papers
- CitationIE: Leveraging the Citation Graph for Scientific Information Extraction
- SciREX: A Challenge Dataset for Document-Level Information Extraction
- Extracting a Knowledge Base of Mechanisms from COVID-19 Papers
- Identification of Tasks, Datasets, Evaluation Metrics, and Numeric Scores for Scientific Leaderboards Construction
- A neural approach for detecting inline mathematical expressions from scientific documents
- Math‑word embedding in math search and semantic extraction
- SemEval-2021 Task 8: MeasEval – Extracting Counts and Measurements and their Related Contexts
- What's in a Measurement? Using GPT-3 on SemEval 2021 Task 8 -- MeasEval
- VILA: Improving Structured Content Extraction from Scientific PDFs Using Visual Layout Groups
- Current Status and Performance Analysis of Table Recognition in Document Images With Deep Neural Networks
- ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select
- Visual Summary Identification From Scientific Publications via Self-Supervised Learning
- Scim: Intelligent Skimming Support for Scientific Papers
- ArguminSci: A Tool for Analyzing Argumentation and Rhetorical Aspects in Scientific Writing
- Generating Scientific Definitions with Controllable Complexity
- Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols
- ACCoRD: A Multi-Document Approach to Generating Diverse Descriptions of Scientific Concepts
- Paper Plain: Making Medical Research Papers Approachable to Healthcare Consumers with Natural Language Processing
- ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports
- Automatic summarization of scientific articles: A survey
- SAPGraph: Structure-aware Extractive Summarization for Scientific Papers with Heterogeneous Graph
- A Platform for Argumentative Zoning Annotation and Scientific Summarization
- SuMe: A Dataset Towards Summarizing Biomedical Mechanisms
- ScisummNet: A Large Annotated Corpus and Content-Impact Models for Scientific Paper Summarization with Citation Networks
- Keyphrase Generation for Scientific Document Retrieval
- Keyphrase Generation Beyond the Boundaries of Title and Abstract
- TLDR: Extreme Summarization of Scientific Documents
- Scientific Paper Extractive Summarization Enhanced by Citation Graphs
- Enhancing scientific papers summarization with citation graph
- On Extractive and Abstractive Neural Document Summarization with Transformer Language Models
- Discourse-aware unsupervised summarization of long scientific documents
- Combination of abstractive and extractive approaches for summarization of long scientific texts
- Learn to Explain: Multimodal Reasoning via Thought Chains for Science Question Answering
- A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers
- Factored Cognition Primer
- Iterated Decomposition: Improving Science Q&A by Supervising Reasoning Processes
- ArgSciChat: A Dataset for Argumentative Dialogues on Scientific Papers
- ScienceQA: a novel resource for question answering on scholarly articles
- ACT2: A multi-disciplinary semi-structured dataset for importance and purpose classification of citations
- Dynamic Context Extraction for Citation Classification
- ACT: an annotation platform for citation typing at scale
- A meta-analysis of semantic classification of citations
- MULTICITE: Modeling realistic citations requires moving beyond the single-sentence single-label setting
- Hierarchical Multi-Label Classification of Scientific Documents
- Benchmark for Research Theme Classification of Scholarly Documents
- CSO Classifier 3.0: a scalable unsupervised method for classifying documents in terms of research topics
- unarXive 2022: All arXiv Publications Pre-Processed for NLP, Including Structured Full-Text and Citation Network
- The Semantic Scholar Open Data Platform
- A Search Engine for Discovery of Scientific Challenges and Directions
- Author Homepage Discovery in CiteSeerX
- Augmenting Scientific Creativity with Retrieval across Knowledge Domains
- Scisight: Combining faceted navigation and research group detection for covid-19 exploratory scientific search
- R-classify: Extracting research papers’ relevant concepts from a controlled vocabulary
- Recommending Research Papers to Chemists: A Specialized Interface for Chemical Entity Exploration
- Aspect-based Document Similarity for Research Papers
- Scientific Paper Recommendation: A Survey
- Bursting Scientific Filter Bubbles: Boosting Innovation via Novel Author Discovery
- Explaining Relationships Between Scientific Documents
- Comparative Graph-based Summarization of Scientific Papers Guided by Comparative Citations
- PaperRobot: Incremental Draft Generation of Scientific Ideas
- Can GPT-3 write an academic paper on itself, with minimal human input?
- SciXGen: A Scientific Paper Dataset for Context-Aware Text Generation
- Automatic Generation of Abstracts for Research Papers
- Comparing scientific abstracts generated by ChatGPT to original abstracts using an artificial intelligence output detector, plagiarism detector, and blinded human reviewers
- SciGen: a Dataset for Reasoning-Aware Text Generation from Scientific Tables
- Learning to Reason for Text Generation from Scientific Tables
- Citation Sentence Generation Leveraging the Content of Cited Papers
- Controllable Citation Text Generation
- AutoCite: Multi-Modal Representation Fusion for Contextual Citation Generation
- Automatic Generation of Citation Texts in Scholarly Papers: A Pilot Study
- CiteBench: A benchmark for Scientific Citation Text Generation
- Citation Recommendation: Approaches and Datasets
- Dual Attention Model for Citation Recommendation
- Contextual citation recommendation using scientific discourse annotation schemes
- To cite, or not to cite? detecting citation contexts in text
- On the use of context for predicting citation worthiness of sentences in scholarly articles
- A Gold Standard Dataset for the Reviewer Assignment Problem
- ReviewerGPT? An Exploratory Study on Using Large Language Models for Paper Reviewing
- Can GPT-4 Perform Neural Architecture Search?
- AutoML-Zero: Evolving Machine Learning Algorithms From Scratch
- Large Language Models Are Human-Level Prompt Engineers
- Autoformalization with Large Language Models
- Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
- NATURALPROVER: Grounded Mathematical Proof Generation with Language Models
- HOList: An Environment for Machine Learning of Higher-Order Theorem Proving
- LeanDojo
- Generating Mathematical Derivations with Large Language Models
- Advancing mathematics by guiding human intuition with AI
- The Ramanujan Machine: Automatically Generated Conjectures on Fundamental Constants
- Generating conjectures on fundamental constants with the Ramanujan Machine
- Discovering faster matrix multiplication algorithms with reinforcement learning
- VizSmith: Automated Visualization Synthesis by Mining Data-Science Notebooks
- Tools and Techniques for Building Programming Assistants for Data Analysis
- Towards Capturing Scientific Reasoning to Automate Data Analysis
- Autonomous discovery in the chemical sciences part I: Progress
- Autonomous discovery in the chemical sciences part II: Outlook
- GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text
- Generative models for molecular discovery: Recent advances and challenges
- A Deep Dive into Machine Learning Density Functional Theory for Materials Science and Chemistry
- Beyond potentials: integrated machine-learning models for materials
- A Generative Approach to Materials Discovery, Design, and Optimization
- Machine learning and the physical sciences
- Solving the quantum many-body problem with artificial neural networks
- Solving high-dimensional partial differential equations using deep learning
- Magnetic control of tokamak plasmas through deep reinforcement learning
- @Machine Learning in Materials Science: From Explainable Predictions to Autonomous Design
- Machine learning in materials informatics: recent applications and prospects
- Highly accurate protein structure prediction with alphafold
- Pre-trained Language Models in Biomedical Domain: A Systematic Survey
- Improved protein structure prediction using potentials from deep learning
- Machine learning applications in genetics and genomics
- Deep learning applications for covid-19
- Applications of machine learning in drug discovery and development
- Can literature analysis identify innovation drivers in drug discovery?
- ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reports
- Scientific Discovery: Computational Explorations of the Creative Process
- Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior
- Science in the age of large language models
- Enhancing Activity Prediction Models in Drug Discovery with the Ability to Understand Human Language
- A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language
- A Text-guided Protein Design Framework
- A deep-learning system bridging molecule structure and biomedical text with comprehension comparable to human professionals
- Translation between Molecules and Natural Language
- Unifying Molecular and Textual Representations via Multi-task Language Modelling
- MolXPT: Wrapping Molecules with Text for Generative Pre-training
- DrugChat: Towards Enabling ChatGPT-Like Capabilities on Drug Molecule Graphs
- Chemberta-2: Towards chemical foundation models
- ChemCrow: Augmenting large-language models with chemistry tools
- Automatic Slide Generation for Scientific Papers
- Can Large Language Models Empower Molecular Property Prediction?
- Accelerating science with human-aware artificial intelligence
- 14 Examples of How LLMs Can Transform Materials Science and Chemistry: A Reflection on a Large Language Model
- ChatGPT for Computational Materials Science: A Perspective
- Prompt engineering of GPT-4 for chemical research: what can/cannot be done?
- @Solving Quantitative Reasoning Problems with Language Models
- Recognizing and Verifying Mathematical Equations using Multiplicative Differential Neural Units
- From ‘F’ to ‘A’ on the N.Y. Regents Science Exams: An Overview of the Aristo Project
- Learning to solve arithmetic problems with a virtual abacus