Recent Posts

• Spurious Rewards: Rethinking Training Signals in RLVR
  by andy12_on 5/27/2025, 5:10:17 PM with 0 comments
• VR-CLI: Learning to Reason for Long-Form Story Generation
  by andy12_on 5/7/2025, 10:15:23 AM with 0 comments
• Tokenformer: Rethinking transformer scaling with tokenized model parameters
  by andy12_on 10/31/2024, 3:35:16 PM with 1 comment
• Selective Attention Improves Transformer
  by andy12_on 10/7/2024, 10:38:33 AM with 1 comment
• The AdEMAMix Optimizer: Better, Faster, Older
  by andy12_on 9/10/2024, 8:00:10 AM with 0 comments