AI that writes: past, present, future In a sweeping survey, Zhang, Guo, Wang, Liang, Hao, and Yu trace how text generation has evolved - from simple templates to neural networks that can draft emails, stories, and more. * From fluency to personality: systems now aim to reflect tone, style, and user
AI
Can AI essay graders be fooled? New research shows many automatic essay scoring (AES) systems reward “word soups” over real writing. Using interpretability tools, the authors found that a few keywords drive most of the score, while flow, grammar, and coherence matter far less. The wild part: because these models
Your face isn’t a password New research shows that a popular way to “lock” face-recognition data—called fuzzy commitments—doesn’t keep it truly safe when used with modern deep‑learning systems. Why? The face templates these systems produce don’t have enough randomness (entropy). That lets attackers reverse
LiDAR lets cars "see" the world, but low-cost sensors often produce sparse, blurry 3D points. This study introduces FLASH, a method that turns low-res scans into high-detail 3D—fast enough for real-time use. How it works * Two domains, one model: FLASH looks at data in space and in
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 inference throughput while handling
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 and
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 (horizontal alignment): learns
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 impact: use language
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. * "Show