Category: Transformer Architecture

• Can LLMs Be Computers?
• Mind-Blowing! MIT Researcher Builds a Computer Inside Transformer: Do LLMs Still Need External Tools?
• Altman Sentences Transformer to Death! AGI Arrives Within Two Years, Next-Gen Architecture on the Way
• "Removing One Layer" Makes the Model Better at Tasks? HIT(SZ) | Yang Shuo's Team Discovers Task-Interfering Layers in VLMs
• ModelBest's SALA Architecture Is Tearing Down the Transformer's Wall
• Transformer Authors Lead Sakana AI to Release Three Papers: Completely Reconstructing Long-Text Memory Mechanisms
• From 'Titans+MIRAS & Nested' Architectural Innovations to NeurIPS2025 Best Paper 'Gated Attention'
• Google AI Roadmap Revealed: Is the Attention Mechanism Being Abandoned? Transformer Has Fatal Flaws!
• ICML 2025 | Fast and Powerful Liger! Transformer Instantly Switches to Linear RNN with only 20M Token Fine-tuning