Recently updated channels

Pick one to see only that channelBrowse all channels →
20VC with Harry Stebbingsyesterday +37AI Engineeryesterday +1硅谷1012 days agoMBMatthew Berman3 days ago +54PragerU3 days agoY Combinator3 days agoa16z4 days ago +1SemiAnalysis4 days agoGOTO Conferences4 days agoThe Builders5 days ago

Results

1 articles
Sort
ChannelMatthew BermanTopicReinforcement LearningLengthOver 30 min
2 slides30:29EN
MBMatthew Berman· Jan 3, 2025How Researchers Think o1-Style Reasoning Models WorkMatthew Berman · Forward FutureMatthew Berman explains a research survey of policy initialization, rewards, search and reinforcement learning, and the open questions behind reasoning models.Reinforcement LearningModels & trainingAI research+1