# Value Residual Learning

arXiv: https://arxiv.org/abs/2410.17897 · HTML: https://mlsanity.com/paper/2410.17897/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in KV cache optimization, one of 12 directions in Efficient LLM inference and serving.
- Builds on 33 of its 41 references that are in the map.
- First posted on arXiv 23 Oct 2024.

## Placed in

- Efficient LLM inference and serving / [KV cache optimization](https://mlsanity.com/inference/kv-cache-optimization/)

## Builds on (most cited first, 30 of 33)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [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)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [HellaSwag: Can a Machine Really Finish Your Sentence?](https://mlsanity.com/paper/1905.07830/) (2019)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering](https://mlsanity.com/paper/1809.02789/) (2018)
- [GLU Variants Improve Transformer](https://mlsanity.com/paper/2002.05202/) (2020)
- [Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling](https://mlsanity.com/paper/2304.01373/) (2023)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [LIMA: Less Is More for Alignment](https://mlsanity.com/paper/2305.11206/) (2023)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [TinyLlama: An Open-Source Small Language Model](https://mlsanity.com/paper/2401.02385/) (2024)
- [DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining](https://mlsanity.com/paper/2305.10429/) (2023)
- [Anti-Oversmoothing in Deep Vision Transformers via the Fourier Domain Analysis: From Theory to Practice](https://mlsanity.com/paper/2203.05962/) (2022)
- [Reducing Transformer Key-Value Cache Size with Cross-Layer Attention](https://mlsanity.com/paper/2405.12981/) (2024)
- [Skywork: A More Open Bilingual Foundation Model](https://mlsanity.com/paper/2310.19341/) (2023)
- [Attention Score is not All You Need for Token Importance Indicator in KV Cache Reduction: Value Also Matters](https://mlsanity.com/paper/2406.12335/) (2024)
- [Revisiting Over-smoothing in BERT from the Perspective of Graph](https://mlsanity.com/paper/2202.08625/) (2022)
- [Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs](https://mlsanity.com/paper/2410.13835/) (2024)

## Built on by (most cited first, 27 of 27)

- [Attention Residuals](https://mlsanity.com/paper/2603.15031/) (2026)
- [On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability](https://mlsanity.com/paper/2608.30320/) (2026)
- [Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation](https://mlsanity.com/paper/2507.02608/) (2025)
- [Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers](https://mlsanity.com/paper/2512.03870/) (2025)
- [ANCRe: Adaptive Neural Connection Reassignment for Efficient Depth Scaling](https://mlsanity.com/paper/2602.09009/) (2026)
- [GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation](https://mlsanity.com/paper/2603.26661/) (2026)
- [You Do Not Fully Utilize Transformer's Representation Capacity](https://mlsanity.com/paper/2502.09245/) (2025)
- [More Expressive Feedforward Layers: Part I. Token-Adaptive Mixing of Activations](https://mlsanity.com/paper/2605.26647/) (2026)
- [Depth-Attention: Cross-Layer Value Mixing for Language Models](https://mlsanity.com/paper/2606.05014/) (2026)
- [YOCO++: Enhancing YOCO with KV Residual Connections for Efficient LLM Inference](https://mlsanity.com/paper/2604.13556/) (2026)
- [Tight Complexity of Muon under Heavy-Tailed Noise](https://mlsanity.com/paper/2605.18528/) (2026)
- [Heuresis: Search Strategies for Autonomous AI Research Agents Across Quality, Diversity and Novelty](https://mlsanity.com/paper/2606.25198/) (2026)
- [Transformers with Selective Access to Early Representations](https://mlsanity.com/paper/2605.03953/) (2026)
- [Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory](https://mlsanity.com/paper/2605.09877/) (2026)
- [SNLP: Layer-Parallel Inference via Structured Newton Corrections](https://mlsanity.com/paper/2605.17842/) (2026)
- [Do Value Vectors in Deep Layers Need Context from the Residual Stream?](https://mlsanity.com/paper/2606.02780/) (2026)
- [Linear Attention Architectures: Mechanisms, Trade-offs, and Cross-Layer Routing](https://mlsanity.com/paper/2607.07953/) (2026)
- [Attention Projection Mixing with Exogenous Anchors](https://mlsanity.com/paper/2601.08131/) (2026)
- [Layer-Parallel Inference Reduces Encrypted Nonlinear Depth in Transformers](https://mlsanity.com/paper/2607.04819/) (2026)
- [WhiteMatter: All-to-All Cross-Layer Connections via KV Source Mixing](https://mlsanity.com/paper/2608.18486/) (2026)
- [One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native Orthography](https://mlsanity.com/paper/2608.25904/) (2026)
- [NeoMME: A Single-Tower Multimodal-Native Multilingual Foundation Encoder for Efficient Fine-Tuning and Inference](https://mlsanity.com/paper/2609.01657/) (2026)
- [Scaling Laws, Tabular Data and Actuarial Ratemaking Models](https://mlsanity.com/paper/2609.03106/) (2026)
- [Depth and Scale in the Sub-150M Regime: JugnuLM-53M vs JugnuLM-110M](https://mlsanity.com/paper/2609.14715/) (2026)
- [MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse Lookup](https://mlsanity.com/paper/2609.15126/) (2026)
- [Bongard: Training Machine Intuition](https://mlsanity.com/paper/2609.39111/) (2026)
- [The Row Normalization Puzzle in Muon](https://mlsanity.com/paper/2609.39114/) (2026)

## Abstract (arXiv)

While Transformer models have achieved remarkable success in various domains, the effectiveness of information propagation through deep networks remains a critical challenge. Standard hidden state residuals often fail to adequately preserve initial token-level information in deeper layers. This paper introduces ResFormer, a novel architecture that enhances information flow by incorporating value residual connections in addition to hidden state residuals. And a variant is SVFormer, where all layers share the first layer's value embedding. Comprehensive empirical evidence demonstrates ResFormer achieves equivalent validation loss with 16.11% fewer model parameters and 20.3% less training data compared to Transformer, while maintaining similar memory usage and computational cost. Besides, SVFormer reduces KV cache size by nearly half with only a small performance penalty and can be integrated with other KV-efficient methods, yielding further reductions in KV cache, with performance influenced by sequence length and cumulative learning rate.