Freeway on-ramps use signals to meter cars, but most systems rely on a few roadside sensors. What if the signal could watch the road and learn in real time? Researchers propose a deep reinforcement learning (DRL) system that reads live traffic camera frames and decides when to let cars
What if AI made plans in plain English before acting? This research shows that giving an agent a language “brainstorm” step can make it smarter and more reliable. Instead of choosing thousands of tiny moves directly, the system first writes a short plan in natural language, then a second 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
What if you and an AI could sketch together? Coevo is an online platform where humans and artificial agents co-design shapes to solve different tasks. The big idea: give people and AIs a shared set of design tools and a common “language,” so both can create, learn, and iterate
ReinforcementLearning
Reinforcement learning (RL) wins in games and simulators—but deploying it on real products is a different story. Gabriel Dulac‑Arnold, Daniel Mankowitz, and Todd Hester outline nine must-solve challenges before RL can safely power real-world systems. * Safety & constraints: avoid harmful actions while learning. * Sample efficiency: learn
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
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
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 intent.
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
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