Research Correspondent
Elena Voss covers model development and the ideas behind new research. Her beat follows the distance between a promising paper and a result that holds up outside the lab. She favors clear explanations, original sources and questions that a benchmark score alone cannot answer.
2,906 published articles · Showing 1341–1360
Researchers have unveiled a novel artificial intelligence technique, dubbed LEAD (Layer-wise Expert-aligned Decoding), that promises to significantly reduce errors in AI-generated radiology reports......
Read article →Lee Douglas, Deep Tech Correspondent A novel and deeply concerning security vulnerability has emerged in the rapidly expanding ecosystem of open-weight Large Language Models (LLMs), threatening to ......
Read article →Researchers have pinpointed distinct neural pathways within Large Language Models (LLMs) that specialize in preserving the meaning of text versus generating grammatically correct output in a new la......
Read article →Lee Douglas, Deep Tech Correspondent Researchers have unveiled a novel artificial intelligence framework, dubbed the "Dual Mind World Model" (DMWM), designed to revolutionize how complex networked ......
Read article →In a significant leap forward for robotics and virtual reality, researchers have unveiled AGILE, a novel AI framework capable of reconstructing intricate hand-object interactions from simple video ......
Read article →A new AI technique promises to shrink 3D scene data by a staggering 1000 times, potentially unlocking immersive virtual experiences for everyday devices. 3D Gaussian Splatting (3DGS) has been a gam......
Read article →The quest for more efficient and accurate AI in e-commerce has taken a significant leap forward with the introduction of RexBERT, a new family of BERT-style encoders meticulously crafted for the nu......
Read article →A significant hurdle in advancing artificial intelligence within healthcare—the ability to train sophisticated models across multiple data types while maintaining strict patient privacy—may soon be......
Read article →Researchers have unveiled novel AI architectures designed to tackle two persistent challenges in the field: catastrophic forgetting in large multimodal models and the need for adaptable solutions i......
Read article →The notoriously complex and error-prone world of smart contract auditing might soon see a seismic shift with the unveiling of SPEAR, a novel multi-agent coordination framework. Developed by researc......
Read article →The relentless march of artificial intelligence, particularly Large Language Models (LLMs), is rapidly reshaping how we create data and manage complex information. Recent research unveiled on arXiv......
Read article →Lee Douglas, Deep Tech Correspondent Artificial intelligence is becoming a crucial tool in dissecting the mechanisms behind online misinformation, with a new study on X.com (formerly Twitter) offer......
Read article →The insatiable hunger of Large Language Models (LLMs) for memory and computational power has long been a bottleneck to their widespread deployment. Now, a novel algorithm-hardware co-design framewo......
Read article →A flurry of new research papers released on arXiv this week unveils significant strides in controlling and optimizing large language models (LLMs), promising more robust, efficient, and nuanced AI ......
Read article →Researchers have unveiled a groundbreaking AI-driven framework that dramatically enhances the design of non-pneumatic tires (NPTs), promising significant leaps in vehicle performance and sustainabi......
Read article →A nuanced understanding of how Large Language Models (LLMs) respond to prompts is critical as they become more integrated into our digital lives, particularly concerning their safety alignment. New......
Read article →Lee Douglas, Deep Tech Correspondent Researchers have unveiled KVSmooth, a novel technique designed to curb the pervasive problem of "hallucination" in multimodal large language models (MLLMs) – a ......
Read article →The decades-old challenge of Simultaneous Localization and Mapping (SLAM) is undergoing a dramatic transformation, thanks to the advent of 3D Gaussian Splatting (3DGS). Traditional SLAM systems, wh......
Read article →Lee Douglas, Deep Tech Correspondent AI assistants are poised to become far more proactive, but a persistent challenge looms: how to make them helpful without being annoying. A new research framewo......
Read article →Artificial intelligence, particularly large language models (LLMs), has long grappled with complex reasoning and planning tasks, often faltering where human cognition excels. A novel approach, insp......
Read article →