A comprehensive index of artificial intelligence and machine-learning research with AI-generated summaries, citation metrics, and direct links to papers and code.
Unknown
This paper argues that AI agents will evolve into modular research infrastructure that reliably connects databases, theory, experiments, and feedback, rather than remaining hype-driven autonomous systems.
Tony Feng, Trieu H. Trinh, G. Bingham, et al.
A case study using Gemini to semi-autonomously evaluate 700 open conjectures from Bloom's Erdős Problems database, finding obscurity rather than difficulty explains their open status.
Karthikeyan Mohanraj, Bagavathy Shanmugam Karthikeyan, R.P. Vivek-Ananth, et al.
IMPPAT is a manually curated database of 1742 Indian medicinal plants, 9596 phytochemicals, and 1124 therapeutic uses, enabling computational drug discovery.
David S. Wishart
DrugBank is a comprehensive bioinformatics/cheminformatics database combining detailed drug data with drug target information for in silico drug discovery.
Nadeem Mehmood, Rosario Culmone, Leonardo Mostarda
Proposes a middleware-based schema model for temporal sensor data storage in MongoDB, enabling flexible schema evolution without losing big data advantages.
Simon Baker, Daniel Scharstein, John Lewis, et al.
Proposes a new benchmark and evaluation methodology for optical flow algorithms, including diverse datasets and improved error metrics, to address challenges in complex natural scenes.
Paul C. D. Hawkins, A. Geoffrey Skillman, Gregory L. Warren, et al.
OMEGA is a systematic, knowledge-based conformer generator validated against high-quality PDB and CSD structures, showing strong performance in reproducing crystallographic conformations.
Jinlong Ru, Peng Li, Jinan Wang, et al.
TCMSP is a systems pharmacology database integrating pharmacochemistry, ADME properties, drug targets, diseases, and interaction networks for 499 Chinese herbs to accelerate drug discovery.
Anna Gaulton, Louisa J. Bellis, A. Patrícia Bento, et al.
ChEMBL is an open-access database of manually curated bioactivity data for drug-like compounds, containing 5.4 million measurements across 1 million compounds and 5200 targets.
Unknown
DataGemma reduces LLM hallucinations by grounding responses in Google's Data Commons statistical database using RIG and RAG methods.
Jinhyuk Lee, Anthony Chen, Zhuyun Dai, et al.
This paper investigates whether long-context language models can replace traditional tools like retrieval systems and databases for knowledge-intensive tasks.
Yasset Pérez‐Riverol, Chakradhar Bandla, Deepti J Kundu, et al.
The PRIDE database 2025 update describes infrastructure improvements, a new chatbot, and enhanced data reuse for MS-based proteomics.