Researchers have analyzed the memory consumption of large language model (LLM) inference on a single NVIDIA H100 GPU. They found that simple analytica...
Researchers have developed a model to evaluate the impact of digital platform governance interventions on various stakeholders. The model represents h...
Researchers have proposed a framework called ReForge that allows an ABR algorithm to adapt to changing network scenarios in real-time. The system uses...
Researchers have developed a tool called CPMpy that can translate high-level constraint satisfaction and optimization problems into different lower-le...
Researchers have developed a training-free framework for correcting SQL errors in Text-to-SQL systems. The system uses a plan-guided, tree-structured ...
Researchers propose a new approach to machine intelligence that focuses on the 'artificial physical world', where objects are intentionally designed a...
Researchers propose a new framework called SkillCommit to improve the performance of large language models (LLMs) without updating their parameters. T...
Researchers have developed a new benchmark called LongRCA Bench to help diagnose problems in long-horizon AI agents. These agents can perform tasks ov...
Researchers have found that adding a single prompt to medical language models, aimed at promoting diversity, equity, and inclusion (DEI), can lead to ...
A new benchmark has been introduced for evaluating automated domain modeling approaches. The benchmark combines two existing datasets, allowing resear...
A new decentralized federated learning method has been proposed for heterogeneous multi-task semantic communication networks. The approach aims to pre...
Researchers propose VibeWorlding, a framework for training and benchmarking multimodal agents that can create 3D open worlds from user queries. They i...