AI
AI images that "think" as they form Most image generators plan before they draw or fix mistakes after. Thinking-while-Generating (TwiG) lets models do something new: interleave short bursts of textual reasoning during generation—like thinking out loud while painting. As pixels appear, the model explains what to add
AI
Can we quickly tell if an image is AI-made — and even which generator produced it — without retraining huge models every month? This study says yes. The authors propose a two-stage system: * Learn a visual "fingerprint" space. A vision model trained with supervised contrastive learning separates real vs. synthetic
AI
Malnutrition screening is often slow and hard to scale. NutriScreener is a new AI tool that flags undernutrition from children’s images and estimates key body measurements to support early intervention. * Blends visual cues with a curated knowledge base matched to a child’s age and region to improve fairness
AI
Spotting AI-made images—without constant retraining Generative models evolve fast, making deepfake detectors go stale. This study introduces a two-stage method that adapts quickly to new image generators. * Stage 1: A vision model learns subtle “fingerprints” via supervised contrastive learning, trained while holding out some generator families to force cross-model
AI
What if AI could learn to translate without any bilingual textbooks? This research shows how pictures can act as a bridge between languages. When we look at the same photo, speakers of different languages describe the same objects and actions. The team uses images as “pivots” so a model can
AI
Look me in the eye, camera. Ever snapped a great photo except your eyes aren’t on the camera? This research introduces GazeCorrection, an AI that subtly redirects your gaze by re-synthesizing just the eye region—keeping your identity and expression intact. How it works: a self-supervised generative model treats
MachineLearning
Training AI usually needs lots of human-labeled examples. This work shows a different path: make models learn from plenty of unlabeled data by asking them to stay consistent under strong "noise." Instead of simple tweaks (like small crops or word drops), they use powerful data augmentation: RandAugment for
AI
Shopping sites host millions of product photos. Some slip through with offensive, non-compliant logos or messages, hurting customers and brands. This paper introduces an AI system that flags those images at massive scale. What’s new: a practical blend of image classification + object detection, tuned for messy, real-world retail catalogs.
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
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-centric learner turns
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 fingers can safely
Robotics
What if robots could learn new tasks just by watching AI-generated videos - and still obey physics? PhysWorld is a new framework that turns text-and-image prompts into physically executable robot skills. * It first generates a task-conditioned video from a single scene image and a command. * Then it reconstructs the scene&