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.

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 ...

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 ...
Hosted on MSN

Breaking the spurious link: How causal models fix offline reinforcement learning's generalization problem

Researchers from Nanjing University and Carnegie Mellon University have introduced an AI approach that improves how machines learn from past data—a process known as offline reinforcement learning.

Is the AI Bubble Real, or Is Relentless Learning Quietly Winning Today?

Is the AI bubble bursting or just noise? Explore continual learning, nested learning, and introspection, plus fixes for ...
EurekAlert!

Reinforcement learning world models for catalyst surface reconstruction: state-of-the-art review

This work presents an AI-based world model framework that simulates atomic-level reconstructions in catalyst surfaces under dynamic conditions. Focusing on AgPd nanoalloys, it leverages Dreamer-style ...
InfoWorld

Are large language models wrong for coding?

The rise of large language models (LLMs) such as GPT-4, with their ability to generate highly fluent, confident text has been remarkable, as I’ve written. Sadly, so has the hype: Microsoft researchers ...
EurekAlert!

Offline model-based reinforcement learning with causal structured world models

The architecture of FOCUS. Given offline data, FOCUS learns a $p$ value matrix by KCI test and then gets the causal structure by choosing a $p$ threshold. After ...