Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers Paper • 2609.32814 • Published 8 days ago • 21
Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs Paper • 2609.29845 • Published 10 days ago • 101
SONAR-LLM: Autoregressive Transformer that Thinks in Sentence Embeddings and Speaks in Tokens Paper • 2508.05305 • Published Aug 7, 2025 • 49