Quick Overview: This is a short presentation introducing the The frontier of LLM research has shifted decisively toward Post-Training and System 2 reasoning. We all know the recipe forĀ ... Speakers: Stephan Zheng, Lead Research Scientist, Salesforce Stephan Zheng (www.stephanzheng.com) leads the AIĀ ...
Accelerating Open Source Rl And - Detailed Overview & Context
This is a short presentation introducing the The frontier of LLM research has shifted decisively toward Post-Training and System 2 reasoning. We all know the recipe forĀ ... Speakers: Stephan Zheng, Lead Research Scientist, Salesforce Stephan Zheng (www.stephanzheng.com) leads the AIĀ ... Mandred Tech is proud to release its first Title: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models (Sep 2025) Link:Ā ... This talk addresses the Training-Inference Mismatch problem commonly encountered in large-scale reinforcement learning (
This video locally installs Open-Reasoner-Zero, which is first In this AI Research Roundup episode, Alex discusses the paper: 'GoLongRL: Capability-Oriented Long Context ReinforcementĀ ... Reasoning models like DeepSeek R1 have demonstrated that learning from interaction is just as critical as learning fromĀ ... At Ray Summit 2025, Fanhai Lu from Contextual AI shares how the company builds enterprise-grade AI agents and applicationsĀ ... In this episode of the AI Research Roundup, host Alex explores a cutting-edge paper on large-scale reinforcement learningĀ ... Have you ever launched an awesome agentic demo, only to realize no amount of prompting will make it reliable enough to deployĀ ...
This paper addresses rollout generation as a major bottleneck in
