Researchers have investigated whether internal representation statistics can provide useful difficulty signals for adaptive inference in multilingual ...
Researchers have identified a trade-off between detecting hate speech and protecting online users' privacy. They found that some hate speech detection...
Researchers have proposed a new framework for evaluating the effectiveness of verifiers used with large language models (LLMs). The Verification Auton...
Researchers from Harvard University have developed an open-source pipeline called Enriched Text that can handle large collections of digitized books. ...
Researchers have developed a method to analyze topic drift in large datasets of text comments, using pre-trained language models to generate embedding...
The ChildSafeAds Shared Task 2026 is a dataset of YouTube videos likely to reach children and teenagers. The task involves identifying commercial cont...
MicroPython and CircuitPython are Python variants designed for microcontrollers in IoT and robotics development. They aim to bring the power of Python...
Researchers have developed a method to control recurrent dynamics in AI models at test time. They found that the behavior of these models can be predi...
Researchers have developed a method to estimate the quality of interactions between humans and robots in real-world environments. They used multimodal...
Researchers have developed a new method for retrieving relevant information from large datasets called Dual-Bounded Relational Recall (DBRR). Unlike t...
Researchers have developed Function+Data Flow (FDF), a visual domain-specific language that enables the composition and reuse of machine learning mode...
Researchers have discovered that vision-language models (VLMs) designed to balance safe generation behavior with grounded visual reasoning may priorit...