Looped Transformers as Programmable Computers
DeepLoop：Depth Scaling for Looped Transformers
The Recurrent Transformer：Greater Effective Depth and Efficient Decoding
SMELT：Scaling Laws for Compute-Matched MoE Looped Transformers
Thinking Deeper, Not Longer：Depth-Recurrent Transformers for Compositional Generalization
Loop, Think, & Generalize：Implicit Reasoning in Recurrent-Depth Transformers
Relaxed Recursive Transformers：Effective Parameter Sharing with Layer-wise LoRA