Category: Neural Networks

• Rotate Attention by 90 Degrees! Today, Kimi's 'Attention Residuals' Takes Off
• Less is More: Recursive Reasoning with Tiny Networks
• Understanding neural networks through sparse circuits
• ByteDance Seed's New Work DeltaFormer: An Attempt at Next-Generation Model Architecture
• Global Attention + Positional Attention Refresh SOTA! Nearly 100% Accuracy!
• 10 Years of Hard Research, Millions Wasted! AI Black Box Remains Unsolvable, Google Breaks Face-off
• Continuous Thought Machines Are Here! Startup by a 'Transformer Eight Sons' Member Launches, Letting AI Stop Making 'One-Step' Snap Decisions