Google’s new AI training method helps small models tackle complex reasoning

Google's SRL framework provides a step-by-step "curriculum" that makes LLMs more reliable for complex reasoning tasks.
IEEE

Trust-Calibrated Human-in-the-Loop Reinforcement Learning for Safe and Efficient Autonomous Navigation

Abstract: Autonomous navigation technology for autonomous ground vehicles (AGVs) is currently a highly active research area. With the advancement of Internet of Things (IoT) technologies, AGVs ...
BMJ

Motor learning principles reported in stroke trials of upper limb task-oriented training: a scoping review

2 Centre for Comprehensive Stroke Rehabilitation and Research, Manipal Academy of Higher Education, Manipal, India Objective Upper limb task-oriented training (UL-TOT) is a complex intervention in ...

Weibo's new open source AI model VibeThinker-1.5B outperforms DeepSeek-R1 on $7,800 post-training budget

Chinese social networking company Weibo's AI division recently released its open source VibeThinker-1.5B —a 1.5 billion ...

Meta’s SPICE framework pushes AI toward self-learning without human supervision

The new reinforcement learning system lets large language models challenge and improve themselves using real-world data ...