Researchers have developed a method to create and validate unknown person names for use in evaluating language models' factuality, privacy leakage, bi...
Researchers have developed a new method for filling in gaps in physiological time-series data, such as blood pressure or glucose levels. The method, c...
Researchers investigated how easily specifications written for one Large Language Model (LLM) can be used with another LLM. They tested this by migrat...
Researchers have discovered a vulnerability in AI systems that can be exploited to make them produce false information. This is known as 'agent memory...
Researchers have proposed AdaptedKG, a method for improving sequential recommendation systems by adapting knowledge graphs to filter out unreliable in...
Researchers have developed EnSI-RAG, a framework for long-document question answering that constructs an entity-centered index to retrieve relevant ev...
Researchers have developed a new method for improving image captioning called Re$^3$Cap. This approach uses retrieval-guided refinement to identify an...
Researchers have developed a new framework called TurboBias 2.0 for improving the accuracy of automatic speech recognition (ASR) systems in production...
Researchers have developed a method called Salt that uses generative AI to verify machine code at scale. This approach inverts the traditional relatio...
Researchers have developed a new method for minimizing convex functions, called Primal Acceleration of Newton's Method. This approach uses only primal...
Researchers have developed an online design method for dynamic networks. This involves designing and building a network over time in response to chang...
Researchers have developed Automated Creatives Quota (ACQ), a framework for determining the optimal number of ad creatives to generate from a single p...