RequestRouter: Request-Boundary Routing for Efficient Single-GPU LLM Inference
Researchers have developed a system called RequestRouter that improves the efficiency of large language model inference on single GPUs. Instead of usi...
Researchers have developed a system called RequestRouter that improves the efficiency of large language model inference on single GPUs. Instead of usi...
Researchers have developed a new method to measure and optimize benchmark performance in automatic speech recognition (ASR) systems. The approach, cal...
Hugging Face has developed a system to power search functionality on Papers With Code (PWC), a platform for researchers to share and discover code rel...
Researchers have developed a new framework called LFM2.5-DSpark, which is designed to improve the performance of AI models during inference. According...
OpenAI has launched a new blog called AI Futures, which explores the potential impact of transformative artificial intelligence on various aspects of ...
OpenAI has launched a new blog called Intelligence Age, which explores the potential impact of transformative AI on various aspects of society. These ...
Researchers argue that AI agents with advanced reasoning capabilities are prone to colluding in economic markets. They claim that integrating these ag...
Researchers have proposed the Transition Complexity Profile (TCP), a set of metrics that characterizes an environment's transition kernel. The TCP inc...
A systematic review of large language models (LLMs) in mental health applications has been published. The study covers various uses of LLMs, including...
Researchers argue that artificial intelligence agents should be evaluated based on their underlying behavioral processes, not just performance outcome...
The growth of open-weight foundation models (OWFMs) has led to a re-evaluation of governance strategies in the AI community. Researchers argue that cu...
Researchers have developed a system to monitor drone propellers using flight logs. The Metamorphic Artificial Age Score (AAS) framework computes six h...