# Residual Matrix Transformers: Scaling the Size of the Residual Stream

arXiv: https://arxiv.org/abs/2506.22696 · HTML: https://mlsanity.com/paper/2506.22696/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 53 references that are in the map.
- First posted on arXiv 28 Jun 2025.

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge](https://mlsanity.com/paper/1803.05457/) (2018)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [Locating and Editing Factual Associations in GPT](https://mlsanity.com/paper/2202.05262/) (2022)
- [The Pile: An 800GB Dataset of Diverse Text for Language Modeling](https://mlsanity.com/paper/2101.00027/) (2020)
- [Transformer Feed-Forward Layers Are Key-Value Memories](https://mlsanity.com/paper/2012.14913/) (2020)
- [Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality](https://mlsanity.com/paper/2405.21060/) (2024)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [On Layer Normalization in the Transformer Architecture](https://mlsanity.com/paper/2002.04745/) (2020)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [RWKV: Reinventing RNNs for the Transformer Era](https://mlsanity.com/paper/2305.13048/) (2023)
- [Retentive Network: A Successor to Transformer for Large Language Models](https://mlsanity.com/paper/2307.08621/) (2023)
- [Scaling Data-Constrained Language Models](https://mlsanity.com/paper/2305.16264/) (2023)
- [Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer](https://mlsanity.com/paper/2203.03466/) (2022)
- [Estimating the Carbon Footprint of BLOOM, a 176B Parameter Language Model](https://mlsanity.com/paper/2211.02001/) (2022)
- [ReZero is All You Need: Fast Convergence at Large Depth](https://mlsanity.com/paper/2003.04887/) (2020)
- [Understanding and Improving Layer Normalization](https://mlsanity.com/paper/1911.07013/) (2019)
- [Will we run out of data? Limits of LLM scaling based on human-generated data](https://mlsanity.com/paper/2211.04325/) (2022)
- [DeepNet: Scaling Transformers to 1,000 Layers](https://mlsanity.com/paper/2203.00555/) (2022)
- [Equinox: neural networks in JAX via callable PyTrees and filtered transformations](https://mlsanity.com/paper/2111.00254/) (2021)
- [NormFormer: Improved Transformer Pretraining with Extra Normalization](https://mlsanity.com/paper/2110.09456/) (2021)
- [Exploiting Deep Representations for Neural Machine Translation](https://mlsanity.com/paper/1810.10181/) (2018)

## Built on by (most cited first, 12 of 12)

- [mHC: Manifold-Constrained Hyper-Connections](https://mlsanity.com/paper/2512.24880/) (2025)
- [Attention Residuals](https://mlsanity.com/paper/2603.15031/) (2026)
- [mHC-lite: You Don't Need 20 Sinkhorn-Knopp Iterations](https://mlsanity.com/paper/2601.05732/) (2026)
- [KromHC: Manifold-Constrained Hyper-Connections with Kronecker-Product Residual Matrices](https://mlsanity.com/paper/2601.21579/) (2026)
- [Deep Delta Learning](https://mlsanity.com/paper/2601.00417/) (2026)
- [FACTUM: Mechanistic Detection of Citation Hallucination in Long-Form RAG](https://mlsanity.com/paper/2601.05866/) (2026)
- [go-mHC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices](https://mlsanity.com/paper/2604.02309/) (2026)
- [GeoNorm: Unify Pre-Norm and Post-Norm with Geodesic Optimization](https://mlsanity.com/paper/2601.22095/) (2026)
- [Learning What to Investigate Next: Meta-Reasoning for Long-Horizon Research Agents](https://mlsanity.com/paper/2610.02525/) (2026)
- [GitSwarm: Decentralized Compounding Inference](https://mlsanity.com/paper/2610.04862/) (2026)
- [The Birkhoff Geometry of Manifold-Constrained Hyper-Connections: Two Channels, Vertex Viscosity, and Sinkhorn as a Retraction](https://mlsanity.com/paper/2610.06653/) (2026)
- [Depth Memory](https://mlsanity.com/paper/2610.18809/) (2026)

## Abstract (arXiv)

The residual stream acts as a memory bus where transformer layers both store and access features (Elhage et al., 2021). We consider changing the mechanism for retrieving and storing information in the residual stream, and replace the residual stream of the transformer with an outer product memory matrix (Kohonen, 1972, Anderson, 1972). We call this model the Residual Matrix Transformer (RMT). We find that the RMT enjoys a number of attractive properties: 1) the size of the residual stream can be scaled independently of compute and model size, improving performance, 2) the RMT can achieve the same loss as the transformer with 58% fewer FLOPS, 25% fewer parameters, and 41% fewer training tokens tokens, and 3) the RMT outperforms the transformer on downstream evaluations. We theoretically analyze the transformer and the RMT, and show that the RMT allows for more efficient scaling of the residual stream, as well as improved variance propagation properties. Code for this project can be found at https://github.com/bmac3/residual-matrix-transformer.