TL;DR LoGo lets large language models pick and blend the right LoRA adapters for each input—no extra training, labels, or task setup. * Training-free: uses signals from a single forward pass to select and weight adapters. * Instance-level: decisions happen on-the-fly for every query. * Practical: keeps
AI
Lowering CT radiation keeps patients safer—but it can make images noisy and blurry. LMM-IQA is an AI that judges low‑dose CT quality and explains what went wrong. * Gives a quality score plus short, plain‑English notes on noise, blur, and contrast loss. * Works without task‑specific training
Lightning Grasp: faster robot gripping Finding a good grip on everyday, irregular tools is still hard for robot hands. Lightning Grasp changes that: it generates diverse, realistic grasps in real time—without training data, delicate parameter tuning, or lucky starting guesses. The trick is a simple Contact Field: a lightweight
Meet AdaRec, a new way to build personalized recommendations with large language models that works even when you have very little data. Instead of hand-crafted features, AdaRec uses narrative profiling—it turns a person’s interactions into plain-language mini-stories the model can understand and explain. * Peer patterns
AutonomousDriving
Teaching self-driving cars to spot the unknown Real roads are messy. To stay safe, autonomous vehicles must notice unexpected hazards—from a toppled ladder to a runaway stroller. That’s the challenge of out-of-distribution (OOD) segmentation. Seungheon Song and Jaekoo Lee propose a simple idea with big
AI
Why do AI models sometimes sound sure while being wrong? This study spotlights a subtle culprit: spurious correlations—strong but misleading patterns in training data (like linking certain surnames to a nationality). * These shortcuts make LLMs produce confident, wrong answers. * Making models bigger doesn’t fix it. * Popular detectors—confidence
AI
AI personas that actually feel human What if our "AI citizens" behaved less like cardboard cutouts and more like real, diverse people? DeepPersona is a generative engine that builds rich, fully narrated synthetic personas at scale. It first assembles a large, hierarchical taxonomy of human attributes by mining
Voice-powered help in the robotic OR During da Vinci robotic surgery, surgeons' hands and eyes are fully occupied, making it hard to pull up scans or labs without breaking focus. A new system—Surgical Agent Orchestrator Platform (SAOP)—turns natural speech into on-screen actions, no clicking required.
Robotics
What's new PhysWorld lets robots learn skills from AI-generated videos—without collecting any real robot data. How it works * Given a task and one photo of the scene, a video model "imagines" a demonstration. * PhysWorld reconstructs a physics-based world from that video. * An object-
AI
Meet AdaRec: smarter recommendations from fewer clicks AdaRec is a new way to personalize recommendations using large language models. Instead of hand-crafted features, it turns your past interactions into short, readable stories—“narrative profiles”—and lets an LLM reason over them with just a few examples. It thinks in
When a self-driving car meets something unusual—a stray sofa, a blown tire—it must flag it as unknown fast. That task is called out-of-distribution (OOD) segmentation. What’s new * Text-driven learning: The model aligns images with language, tapping rich word knowledge to recognize a wider
AI
Large language models can sound confident even when they are wrong. This study pinpoints a sneaky culprit: spurious correlations — statistical shortcuts like linking certain surnames to a nationality. Models absorb these patterns from data and then answer with high certainty, even when the link is false. What the researchers found