AI
DeepPersona in a nutshell Researchers built a generative engine that creates richly detailed, realistic synthetic personas for AI—without using private personal data. * Deeper profiles: Each persona includes hundreds of structured attributes and about 1 MB of narrative text—roughly 100x more detail than prior work. * Big taxonomy: A hierarchy
FLASH: Sharper, faster LiDAR from low-cost sensors Turning sparse laser scans into rich 3D views is hard and slow—until now. FLASH (Frequency-aware LiDAR Adaptive Super-resolution with Hierarchical fusion) upgrades low-resolution LiDAR to high detail in real time. * Dual-domain smarts: Combines local spatial attention with
AI
In robotic surgery, a surgeon’s hands and eyes are busy. That makes it hard to pull up labs, flip through CT slices, or inspect 3D anatomy without breaking focus. This study introduces the voice-directed Surgical Agent Orchestrator Platform (SAOP): a coordinated team of AI agents that listens to
Robotics
What if robots could decide how to grasp anything—tools, toys, odd-shaped parts—in real time? Lightning Grasp delivers orders-of-magnitude speedups for dexterous robotic hands, while keeping results diverse and reliable. The trick is a simple data structure called a Contact Field: it precomputes where and how
What if AI didn’t just flag false claims—but showed its work? ED2D is a new “multi‑agent debate” system where multiple AI voices argue and retrieve evidence to judge online claims—and explain why. * Outperforms prior methods on three misinformation detection benchmarks. * When ED2D is correct, its debunking
AI in healthcare must do more than translate Millions of patients in the U.S. who prefer Spanish or other languages face barriers that go far beyond words. This study asked 14 patient navigators how AI tools could help—or harm—care for Spanish-speaking patients with limited English proficiency
Safer CT scans, clearer answers Low‑dose CT reduces radiation, but can introduce noise, blur, and contrast loss. LMM‑IQA is an AI system that scores image quality and explains what went wrong—using plain language. * Dual output: a numerical quality score plus text describing issues like noise, blur, or
AI
Imagine telling your phone what you want—and an AI taps, types, and swipes to get it done. This paper introduces DigiData, a large, diverse, multi‑modal dataset designed to train general‑purpose mobile control agents. Instead of relying on unstructured user logs, the team systematically explores app features to
AI
TL;DR LoRA adapters are small plug-in modules that fine-tune big language models cheaply. But one adapter per task doesn’t fit messy, real-world inputs. What’s new LoRA on the Go (LoGo) lets a model pick and blend the best adapters for each individual input—no
What if we could A/B test content moderation without exposing real people? Researchers Giacomo Fidone, Lucia Passaro, and Riccardo Guidotti built an LLM‑powered simulator that runs parallel, counterfactual versions of the same online conversation—one with a moderation policy, one without—keeping everything else equal. This lets platforms
AI
What if AI could argue with itself to spot misinformation—and change minds? Researchers introduce ED2D, an evidence-based multi-agent debate system. It doesn’t just label claims; it retrieves factual sources and generates clear debate transcripts so people can see the reasoning. * Outperforms prior methods on multiple detection
AI
Millions of U.S. patients with limited English proficiency face more than a “just translate it” problem. This study asks: how could AI help Spanish‑speaking patients—and where might it make things worse? * What they did: Interviewed 14 patient navigators using storyboards of AI for on‑demand translation and