Recent Posts

• Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Traces
  by hislazinesson 10/23/2024, 3:51:45 AM with 2 comments
• Dive into Deep Learning
  by hislazinesson 3/2/2024, 10:44:29 AM with 1 comment
• Pretraining data enables narrow selection capabilities in transformer models
  by hislazinesson 11/7/2023, 4:51:41 PM with 11 comments
• Google / DeepMind Launches SynthID
  by hislazinesson 8/30/2023, 6:56:02 AM with 1 comment
• CS25 Stanford Seminar – Introduction to Transformers with Andrej Karpathy
  by hislazinesson 5/31/2023, 8:16:43 AM with 1 comment
• Fast Transformer Decoding: One Write-Head Is All You Need
  by hislazinesson 5/30/2023, 4:17:37 PM with 1 comment