Papers with Code 아카이브

scientific discovery

태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.

전체 기법전체 데이터셋

하위 태스크

0

평가표

0

보존된 평가 기록

0

코드

관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.

https://github.com/AgentForceTeamOfficial/Baby-AIGS

공식 코드

AIGS: Generating Science from AI-Powered Automated Falsification

https://github.com/Ale9806/eVLLM

공식 코드

μ-Bench: A Vision-Language Benchmark for Microscopy Understanding

https://github.com/Baran-phys/DynamicFormer

공식 코드

Can Transformers Do Enumerative Geometry?

https://github.com/CitrineInformatics-ERD-public/linear-vs-blackbox

공식 코드

Interpretable models for extrapolation in scientific machine learning

https://github.com/Dandelionym/llm_for_mechanisms

공식 코드

Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?

https://github.com/DataSlingers/unsupervised-workflow-astro

공식 코드

Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices

https://github.com/Future-House/BixBench

공식 코드

BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology

https://github.com/Future-House/data-analysis-crow

공식 코드

BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology

https://github.com/GraphPKU/GeoRCG

공식 코드

Geometric Representation Condition Improves Equivariant Molecule Generation

https://github.com/IBM/AI-Hilbert

공식 코드

Evolving Scientific Discovery by Unifying Data and Background Knowledge with AI Hilbert

https://github.com/IsmailAlaouiAbdellaoui/EQL-Wind-Speed-Forecasting

공식 코드

Symbolic regression for scientific discovery: an application to wind speed forecasting

https://github.com/MIC-DKFZ/nnunet

공식 코드

Automated Design of Deep Learning Methods for Biomedical Image Segmentation

https://github.com/MLResearchAtOSRAM/cause2e

공식 코드

Quantitative probing: Validating causal models using quantitative domain knowledge

https://github.com/MasterAI-EAM/MatEmbedding

공식 코드

From Tokens to Materials: Leveraging Language Models for Scientific Discovery

https://github.com/NBoulle/greenlearning

공식 코드

Data-driven discovery of Green's functions with human-understandable deep learning

https://github.com/Networks-Learning/differentiable-learning-under-triage

공식 코드

Differentiable Learning Under Triage

https://github.com/NoviScl/AI-Researcher

공식 코드

Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers

https://github.com/PaddlePaddle/PaddleHelix

공식 코드

Unifying Sequences, Structures, and Descriptions for Any-to-Any Protein Generation with the Large Multimodal Model HelixProtX

https://github.com/PharMolix/OCSU

공식 코드

OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery

https://github.com/PingchuanMa/SGA

공식 코드

LLM and Simulation as Bilevel Optimizers: A New Paradigm to Advance Physical Scientific Discovery

https://github.com/Ryan-Rhys/Heteroscedastic-BO

공식 코드

Applications of Gaussian Processes at Extreme Lengthscales: From Molecules to Black Holes

https://github.com/SymposiumOrganization/NeuralSymbolicRegressionThatScales

공식 코드

Neural Symbolic Regression that Scales

https://github.com/ZonglinY/MOOSE-Chem

공식 코드

MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses

https://github.com/adammoss/aicosmologist

공식 코드

The AI Cosmologist I: An Agentic System for Automated Data Analysis

https://github.com/agenttorch/agenttorch

공식 코드

On the limits of agency in agent-based models

https://github.com/alecgower/lgemplus

공식 코드

LGEM$^\text{+}$: a first-order logic framework for automated improvement of metabolic network models through abduction

https://github.com/alibaba/graph-gpt

공식 코드

GraphGPT: Graph Learning with Generative Pre-trained Transformers

https://github.com/allenai/discoveryworld

공식 코드

DISCOVERYWORLD: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents

https://github.com/amair-lab/piflow

공식 코드

PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration

https://github.com/andresalgaba/llms_scientific_literature

공식 코드

How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?

https://github.com/anikethh/iris-interactive-research-ideation-system

공식 코드

IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery

https://github.com/antoninschrab/fl-mmdagg

공식 코드

AutoML Two-Sample Test

https://github.com/arkadaw9/PGNN

공식 코드

Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling

https://github.com/artificial-scientist-lab/ariadnevr

공식 코드

Virtual Reality for Understanding Artificial-Intelligence-driven Scientific Discovery with an Application in Quantum Optics

https://github.com/artificial-scientist-lab/deepgraphdreaming

공식 코드

Deep Quantum Graph Dreaming: Deciphering Neural Network Insights into Quantum Experiments

https://github.com/aspuru-guzik-group/gemini

공식 코드

Gemini: Dynamic Bias Correction for Autonomous Experimentation and Molecular Simulation

출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.