# Attention Sinks and Outliers in Attention Residuals

arXiv: https://arxiv.org/abs/2605.17887 · HTML: https://mlsanity.com/paper/2605.17887/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 62 references that are in the map.
- First posted on arXiv 18 May 2026.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [Pointer Sentinel Mixture Models](https://mlsanity.com/paper/1609.07843/) (2016)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [What Does BERT Look At? An Analysis of BERT's Attention](https://mlsanity.com/paper/1906.04341/) (2019)
- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Universal Transformers](https://mlsanity.com/paper/1807.03819/) (2018)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [SpinQuant: LLM quantization with learned rotations](https://mlsanity.com/paper/2405.16406/) (2024)
- [Reducing Transformer Depth on Demand with Structured Dropout](https://mlsanity.com/paper/1909.11556/) (2019)
- [OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models](https://mlsanity.com/paper/2308.13137/) (2023)
- [QuIP: 2-Bit Quantization of Large Language Models With Guarantees](https://mlsanity.com/paper/2307.13304/) (2023)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [Revealing the Dark Secrets of BERT](https://mlsanity.com/paper/1908.08593/) (2019)
- [DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads](https://mlsanity.com/paper/2410.10819/) (2024)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Mixture-of-Depths: Dynamically allocating compute in transformer-based language models](https://mlsanity.com/paper/2404.02258/) (2024)
- [FastBERT: a Self-distilling BERT with Adaptive Inference Time](https://mlsanity.com/paper/2004.02178/) (2020)
- [When Attention Sink Emerges in Language Models: An Empirical View](https://mlsanity.com/paper/2410.10781/) (2024)
- [LoftQ: LoRA-Fine-Tuning-Aware Quantization for Large Language Models](https://mlsanity.com/paper/2310.08659/) (2023)
- [Outlier Suppression: Pushing the Limit of Low-bit Transformer Language Models](https://mlsanity.com/paper/2209.13325/) (2022)

## Built on by (most cited first, 2 of 2)

- [Low-Rank Attention Residuals](https://mlsanity.com/paper/2607.09694/) (2026)
- [Abstention and Noise Filtering: Two Missing Primitives of Softmax Attention](https://mlsanity.com/paper/2609.22005/) (2026)

## Abstract (arXiv)

We propose OASIS, an outlier- and sink-aware method that stabilizes dual-normalized attention-residual architectures through explicit null routing and token-to-depth null coupling. AttnResidual introduces an additional depth-wise normalization channel that improves inter-layer routing flexibility but can also amplify attention sinks, activation outliers, and low-bit quantization error. OASIS builds on explicit Softmax1-based null routes at both the token and depth levels and uses token-level null evidence to downweight depth branches exhibiting stronger null behavior. Theoretically, we characterize a conditional mechanism for sink-like attention concentration under dual normalization, offering insight into the low-bit sensitivity observed in AttnResidual. Experimentally, we compare OASIS against five baselines on three language-model backbones and multiple language-modeling, reasoning, and long-context benchmarks and observe consistent improvements in both attention sink mitigation and post-quantization performance. Notably, relative to Vanilla AttnResidual, OASIS reduces maximum infinity norm by 81.75% and average kurtosis by 95.90%, lowers W8A8 perplexity by 82.00%, and improves W4A4 GSM8K Pass@1 by 42.11% on average across LLaMA-3.2-1B, Qwen3-0.6B, and Phi-4. Code is available at: https://github.com/robinzixuan/OASIS.