Category: Model Architecture

• Mamba-3
• Rotate Attention by 90 Degrees! Today, Kimi's 'Attention Residuals' Takes Off
• Breaking Static Model Weights! Tencent Hunyuan Releases Real-Time Brain-Switching Technology for Inference
• Stop Clipping Aggressively! Qwen Proposes GatedNorm, Unifying the Perspective on Residual Flow Mysteries
• Less is More: Recursive Reasoning with Tiny Networks
• Zhipu's New Model Also Uses DeepSeek's MLA, Runs on Apple M5
• Wenfeng Liang Signs, DeepSeek Kicks Off New Year with a New Macro Architecture Chapter, Cracking the Gradient Explosion and Memory Wall