Topic
real-time
Supply Chain Project44 splits into two businesses, launches AI-native LSP44 for logistics providers
Project44 announced it is separating into two focused businesses: project44 for enterprise shippers and LSP44, a dedicated AI-native infrastructure business for logistics service providers. The split addresses the different buying needs of shippers and LSPs, with LSP44 leveraging over a decade of network data and AI agents.
Technology Samsara Ride Along pushes fleet safety AI beyond incident flagging to continuous driver monitoring
Samsara introduced Ride Along at its Beyond 2026 conference, an AI feature that conducts virtual ride-alongs of 10-30 minutes to produce a full behavioral picture of drivers, shifting from rare incident flagging to continuous positive reinforcement. UNFI was an early beta tester, and the company also announced an in-cab conversational AI agent.
Physical Atari Platform Offers Low-Cost Robotics Testbed for Reinforcement Learning Research
Researchers have developed Physical Atari, a platform combining a robot (Robotroller) with an Atari gaming system to study real-time reinforcement learning (RL) on physical robots. The system costs under $1,000 and uses off-the-shelf components and 3D-printed parts. It has been validated in weeks-long continuous experiments without mechanical failure, demonstrating that RL algorithms can learn directly on robots but suffer performance drops from small distribution shifts.
JoyAI-VL-Interaction Model Brings Real-Time Vision-Language AI to Enterprise Applications
JoyAI-VL-Interaction is an open-source, 8B-scale vision-language model that continuously monitors video streams and decides in real time whether to stay silent, speak, or delegate to a background model. Human raters preferred it over Doubao and Gemini in six real-world scenarios. The system includes pluggable ASR/TTS, memory, and API integration.
GPU-Free AI Model UltraSeg Enables Real-Time Ultrasound Segmentation on CPUs
UltraSeg, an ultra-lightweight AI architecture, enables real-time point-of-care ultrasound segmentation without GPU dependency. Running on single-core CPUs at up to 89.7 FPS, it matches or exceeds larger models like UNet, making AI diagnostics viable in resource-limited settings.
MimicIK Framework Achieves Real-Time Inverse Kinematics with 4.65 mm Accuracy for Robotic Teleoperation
MimicIK, a new generative inverse kinematics framework, learns smooth joint-space motion priors from teleoperation demonstrations using conditional flow matching. It achieves a mean position error of 4.65 mm, a 92.01% success rate within 10 mm, and reduces inference latency to 6.74 ms, enabling robust 20 Hz real-time control. The framework introduces an FK consistency loss to enforce task-space accuracy.