awesome-artificial-intelligence-research
github.com/thyrixyang/awesome-artificial-intelligence-research ↗A curated list of Artificial Intelligence (AI) Research, tracks the cutting edge trending of AI research, including recommender systems, computer vision, machine learning, etc.
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me computer vision resources from awesome-artificial-intelligence-research"
Installation instructions →What's inside
Multimodal, Vision-Language, and Generative AI
- 3D Gaussian Splatting PapersComputer Vision
actively maintained 3D Gaussian Splatting paper tracker, including conference-specific lists.
- 3D Point CloudComputer Vision
point cloud deep learning resources.
- Awesome Autonomous VehiclesEmbodied AI, Robotics, and World Models
self-driving and autonomous vehicle resources.
- Awesome CBIR PapersComputer Vision
image retrieval and content-based image retrieval.
- Awesome Crowd CountingComputer Vision
crowd counting papers and datasets.
- Awesome Deep VisionComputer Vision
classic deep vision resources with high historical value.
Core Machine Learning Research
- Adversarial Machine LearningRobustness, Interpretability, and Learning Paradigms
adversarial ML papers and resources.
- AutoML PapersGeneral ML, Surveys, and Methods
automated machine learning papers and tutorials.
- Awesome Architecture SearchGeneral ML, Surveys, and Methods
neural architecture search resources.
- Awesome AutoDLGeneral ML, Surveys, and Methods
automated deep learning and neural architecture search.
- Awesome Causality AlgorithmsGeneral ML, Surveys, and Methods
causal discovery and inference algorithms.
- Awesome Community DetectionGraph Learning and Knowledge Graphs
community detection papers.
Research Feeds, Benchmarks, and Model/Data Hubs
- AgentBenchModels, Datasets, and Evaluation
benchmark and leaderboard for evaluating LLM agents across interactive environments.
- AndroidWorldModels, Datasets, and Evaluation
environment and benchmark for autonomous agents operating Android apps through an emulator.
- ARC-AGIModels, Datasets, and Evaluation
abstraction-and-reasoning benchmark for testing generalization on novel visual puzzle tasks.
- Artificial AnalysisModels, Datasets, and Evaluation
independent benchmark hub for language, multimodal, speech, agent, provider, and hardware comparisons.
- arXiv SanityPaper Discovery and Code
arXiv search and paper recommendation.
- AstaBenchModels, Datasets, and Evaluation
benchmark suite and leaderboards for evaluating agents on scientific research tasks.
Foundation Models, LLMs, and Agents
- AgentHarmAlignment, Safety, Security, and Trustworthiness
benchmark for harmful multi-step LLM agent tasks and jailbreak robustness.
- Awesome Agent MemoryAgent Protocols, Memory, and Tooling
papers, systems, and benchmarks for long-term memory, context engineering, retrieval, and reasoning in agents.
- Awesome Agents for ScienceAI Agents
LLM agents for scientific research and development.
- Awesome AI Agent PapersAI Agents
weekly updated 2026 agent research papers on memory, tools, evaluation, workflows, and security.
- Awesome AI AgentsAI Agents
autonomous agent projects and resources.
- Awesome AI AlignmentAlignment, Safety, Security, and Trustworthiness
alignment research resources and reading paths.
Domain Applications
- AIRS-BenchScience, Medicine, and Quant
benchmark and evaluation code for AI research science agents on tasks from machine learning papers.
- Anomaly Detection ResourcesAnomaly Detection
anomaly detection papers, books, code, and datasets.
- Awesome AI Agents for HealthcareScience, Medicine, and Quant
healthcare agentic AI papers and resources.
- Awesome AI for ResearchScience, Medicine, and Quant
AI-for-research papers and systems organized by research stage, role, domain, and evaluation.
- Awesome AI for ScienceScience, Medicine, and Quant
AI tools, papers, datasets, and frameworks for scientific discovery.
- Awesome AI ScientistScience, Medicine, and Quant
survey-style collection on AI scientists, AI researchers, AI engineers, and automated research pipelines.
Showing a sample of 218 resources. View the full list on GitHub →