
AgML
A centralized framework for agricultural machine learning.
Highlighted datasets, code, and tools from National AI Institutes
Browse the complete collection of datasets, code, platforms, and benchmarks
85 resources

A centralized framework for agricultural machine learning.

Platform to design molecules, plan synthesis routes, and optimize chemical processes.

First rigorous benchmark for advancing multimodal dataset creation.

A quality-controlled food knowledge graph constructed from scientific literature with large language models.

Cyberinfrastructure services for automated data labeling, image segmentation, model serving, and edge deployment, usable across any field.

An interpretable neural network that helps scientists discover mathematical and physical laws

Data synthesis pipeline generating high-quality alignment data for LLMs

The state-of-the-art open-source platform to design, simulate, and train AI-based robots.

MutateEverything predicts the effect of all single and double protein mutations in one forward pass. It is even versatile enough to predict higher-order mutations with minimal computational overhead.

Compute, commercial cloud, data, models and more at no cost to US-based AI researchers!

An open source implementation of OpenAI's CLIP

An open-source framework for training large multimodal models

Research platform for open-source, end-to-end Open RAN experimentation.

Democratizing Hardware Design: leading open-source application for semiconductor digital design

Fully open data curation for reasoning models

Python Dynamic Mode Decomposition

Package for the sparse identification of nonlinear dynamical systems from data

Synthesizing 1.5M Tool-Agentic Data from Real-World MCP Environments

Security research resource/tool for analyzing 5G/6G network specifications or vulnerabilities.

ACCESS helps researchers and educators utilize the nation’s advanced computing systems and services – at no cost to you.

Benchmark to evaluate AI agriculture advisory services.

AI tools for adult and online education: personalized tutoring, virtual teaching assistants, and interactive learning.

Public agricultural datasets for computer vision: livestock tracking, pest detection, and ag-robotics navigation.

Curated educational resources from 30 leading AI research institutions to help you explore and master AI skills at every level.

Open-source, reconfigurable software for autonomous vehicle design, implementation, test, and analysis.

Benchmark for assessing VLMs' capabilities in plant stress phenotyping

A lightweight learning-based trajectory optimization framework for Quadrotors

ASCII Art-based Jailbreak Attacks against Aligned LLMs

First benchmark for both scientific computing and visualization in the astronomy domain.

Behavioral Analysis via Self-Supervised Transformers

Zero-Shot Detection of LLM-Generated Text

A Large Curated Image Dataset Enabling AI for Biodiversity

Python package for processing neural data into a standardized format.

BPDB maps and quantifies agricultural byproducts, unlocking their potential for reuse in industries like nutraceuticals, cosmetics, and more.

Enzyme function prediction from amino-acid sequence, outperforming the previous standard for annotating understudied, mislabeled, and multi-function enzymes.

Cost-Aware Exploration in LLM Agents

Detecting inconsistencies in 4G/5G cellular network specifications and derived dataset

LLM querying for complex scientific reasoning in catalyst design.

AI-guided method for molecule optimization campaigns.

Dark Matter and Astrophysics with Machine learning and Simulations

Tool for robust motion correction in high-density extracellular recordings across different species.

Providing a thorough assessment of trustworthiness in GPT models

GPU-enabled fast and scalable solver for training kernel machines

NSF-funded research infrastructure consisting of distributed computing and storage resources located at 35 national and international sites interconnected by high-bandwidth networks

High-Fidelity RF Signal Mapping Using Geographic Databases

Compact and Efficient Genome Sketching using Hyperdimensional Vectors

Hypergraph Partitioning for VLSI: Benchmarks, Code and Leaderboard

A benchmark dataset pairing molecules with natural-language descriptions, for models that connect chemistry and language.

A Comprehensive Framework for Benchmarking Label-Efficient Learning

Malware Analysis Benchmark for Artificial Intelligence and Machine Learning

Multi Agent-based Research Validator and Enabler using Large Language Models

ACCESS MATCH Services connects researchers with professionals to help solve their research problems.

Open platform to train and deploy AI atmospheric prediction models

MILES GUESS provides Keras and Pytorch implementations of evidential deep learning models and supports analysis of aleatoric and epistemic uncertainties.

Neuromechanical Emulation of Animal Behavior

Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Datasets from real-world 5G measurement studies over cellular networks, aerial/drone 5G, carrier aggregation, radio-access failures, and misconfigurations.

Open implementation of Google Brain's Circuit Training (Morpheus) deep RL-based placement method

Web-based platform for running neuroscience and behavioral experiments online.

Normalized cuts for scalable clustering and segmentation, enabling efficient detection of structure in high-dimensional data and learned representations.

Training a foundation model for materials on a budget

Enabling Real-Time AI-Based Open RAN Control

Benchmark for prompt injection attacks and defenses in LLMs

A centralized, AI-powered repository for preclinical animal research.

A package for computing data-driven approximations to the Koopman operator

Methods for numerical differentiation of noisy data in python

PySensors is a Python package for sparse sensor placement

Platform for RF datasets and data-generation workflows for wireless and radio-frequency machine learning.

Chemical reaction extraction from scientific literature

Risky Code Execution and Generation Benchmark for Code Agents

Continual learning engine for AI agents: a system that converts experience into continuous, regression-aware improvement.

Support science gateways through proposal development assistance, technical consultancy on system architecture, user experience consultancy, and sustainability training.

Semantic LIDAR odometry and mapping for cylinderical objects (e.g. trees in forests)

Distributed coordination and resource allocation benchmarks for evaluating multi-agent autonomy.

Framework and dataset for generating vectorized HD maps from vehicle sensors.

Sparse, Lightweight, Decentralized Metric-Semantic SLAM for Multi-Robot Navigation

Sparse Continual Learning on the Edge

Traffic analysis and classification tool for Open RAN

Python package for easily working with temporal data.

First semantically segmented LiDAR dataset collected with robotic systems in agricultural environments.

The first open-source, constraints-driven partitioner for RTL-to-GDS tools, recently updated with timing-driven capabilities and improved runtime.

Evading Watermark based Detection of AI-Generated Content

Cross-platform toolbox for molecule manipulation and combinatorial library generation.

Jailbreaking Text-to-image Generative Models

A PyTorch-friendly open-source library for learning from Neural Data. Helps you write efficient training pipelines and models.