A faster, systematic way to train large language models for enterpriseResearchKim Martineau07 Mar 2024AIFoundation ModelsGenerative AI
An AI model trained on data that looks real but won’t leak personal informationResearchKim Martineau12 Dec 2023AIAI PrivacyData and AI SecurityFinanceFoundation Models
The latest AI safety method is a throwback to our maritime pastResearchKim Martineau16 Nov 2023AIAI TransparencyExplainable AIFairness, Accountability, TransparencyGenerative AI
What is AI alignment?ExplainerKim Martineau08 Nov 2023AIAutomated AIFairness, Accountability, TransparencyFoundation ModelsNatural Language Processing
Find and fix IT glitches before they crash the system NewsKim Martineau28 Sep 2023AI for CodeAI for ITExplainable AIFoundation ModelsGenerative AI
An open-source toolkit for debugging AI models of all data typesTechnical noteKevin Eykholt and Taesung Lee08 Sep 2023Adversarial Robustness and PrivacyAI TestingData and AI Security
What is retrieval-augmented generation?ExplainerKim Martineau22 Aug 2023AIExplainable AIGenerative AINatural Language ProcessingTrustworthy Generation
Did an AI write that? If so, which one? Introducing the new field of AI forensicsExplainerKim Martineau24 Jul 2023Adversarial Robustness and PrivacyAIExplainable AIFoundation ModelsGenerative AITrustworthy AI
Researchers validate a new class of AI-generated Covid antiviralsNewsKim Martineau28 Jun 2023Accelerated DiscoveryAIFoundation ModelsGenerative AITrustworthy AI
AI Privacy Toolkit gets a boost on dataset assessment in latest releaseTechnical noteMaya Anderson and Abigail Goldsteen16 Jun 2023AI PrivacySecurity
AI diffusion models can be tricked into generating manipulated imagesNewsKim Martineau05 Jun 2023AIAI TestingData and AI SecurityFoundation ModelsGenerative AISecurity
IBM’s Stacy Hobson wants to build tech that works for everyoneResearchKim Martineau24 Feb 2023AIFairness, Accountability, TransparencyHuman-Centered AIResponsible Technology
What is prompt-tuning?NewsKim Martineau15 Feb 2023AIComputer VisionFairness, Accountability, TransparencyFoundation ModelsMachine LearningNatural Language Processing
Saška Mojsilović wants to channel AI for good. She may also make you rethink sour cabbageNewsKim Martineau09 Feb 2023AI TransparencyData and AI SecurityExplainable AIFairness, Accountability, TransparencyMachine Learning
DOFramework: A testing framework for decision optimization model learnersTechnical noteOrit Davidovich02 Feb 2023AIAI TestingMathematical Sciences