AI Publications

IBM Research is tackling some of AI's greatest challenges. Our scientists and engineers focus on fundamental scientific breakthroughs to help guide the advancement of AI. Browse some of our latest publications spanning a wide range of core AI disciplines.

Filter papers

Research area

Choose research area

Adversarial Networks

Conversational Systems

Computer vision

Deep Learning

Hardware and Architectures for AI

Machine Learning

Natural Language Processing

Recurrent Neural Networks

Reinforcement Learning


Trusting AI

Recent conferences

Choose conference

ICLR (2019)

AAAI (2019)

NeurIPS (2018)

EMNLP (2018)

KDD (2018)

ACL (2018)


ICML (2018)

CVPR (2018)

AAAI (2018)

ICLR (2018)

AIES (2018)

NeurIPS (2017)

CVPR (2017)

IAAI (2017)

Search papers


The new frontiers of AI: Selected publications from 2018

Explore featured collections of IBM AI research papers from 2018 on advancing, scaling, and trusting AI.


Project Debater

Project Debater is the first AI system that can debate humans on complex topics. Project Debater digests massive texts, constructs a well-structured speech on a given topic, delivers it with clarity and purpose, and rebuts its opponent. Explore the research that drives many of Project Debater’s capabilities.

Recent conferences

ICLR (2019)

AAAI (2019)


NeurIPS (2018)

EMNLP (2018)


Equivalent-accuracy accelerated neural-network training using analogue memory

A path towards hardware accelerators that are both fast and energy efficient, particularly on fully connected neural-network layers.

Quantum and AI

Demonstration of quantum advantage in machine learning