# Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models

arXiv: https://arxiv.org/abs/2406.12311 · HTML: https://mlsanity.com/paper/2406.12311/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 37 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Builds on (most cited first, 30 of 32)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [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)
- [OPT: Open Pre-trained Transformer Language Models](https://mlsanity.com/paper/2205.01068/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [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)
- [PIQA: Reasoning about Physical Commonsense in Natural Language](https://mlsanity.com/paper/1911.11641/) (2019)
- [BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions](https://mlsanity.com/paper/1905.10044/) (2019)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://mlsanity.com/paper/2306.00978/) (2023)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [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)
- [ST-MoE: Designing Stable and Transferable Sparse Expert Models](https://mlsanity.com/paper/2202.08906/) (2022)
- [SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression](https://mlsanity.com/paper/2306.03078/) (2023)
- [LLM-QAT: Data-Free Quantization Aware Training for Large Language Models](https://mlsanity.com/paper/2305.17888/) (2023)
- [SqueezeLLM: Dense-and-Sparse Quantization](https://mlsanity.com/paper/2306.07629/) (2023)
- [A Survey on Model Compression for Large Language Models](https://mlsanity.com/paper/2308.07633/) (2023)
- [Binary Neural Networks: A Survey](https://mlsanity.com/paper/2004.03333/) (2020)
- [BitNet: Scaling 1-bit Transformers for Large Language Models](https://mlsanity.com/paper/2310.11453/) (2023)
- [ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions](https://mlsanity.com/paper/2003.03488/) (2020)
- [TernaryBERT: Distillation-aware Ultra-low Bit BERT](https://mlsanity.com/paper/2009.12812/) (2020)
- [BiLLM: Pushing the Limit of Post-Training Quantization for LLMs](https://mlsanity.com/paper/2402.04291/) (2024)
- [OWQ: Outlier-Aware Weight Quantization for Efficient Fine-Tuning and Inference of Large Language Models](https://mlsanity.com/paper/2306.02272/) (2023)
- [PB-LLM: Partially Binarized Large Language Models](https://mlsanity.com/paper/2310.00034/) (2023)
- [OneBit: Towards Extremely Low-bit Large Language Models](https://mlsanity.com/paper/2402.11295/) (2024)
- [Evaluating Quantized Large Language Models](https://mlsanity.com/paper/2402.18158/) (2024)

## Built on by (most cited first, 14 of 14)

- [Quantization Error Propagation: Revisiting Layer-Wise Post-Training Quantization](https://mlsanity.com/paper/2504.09629/) (2025)
- [ARB-LLM: Alternating Refined Binarizations for Large Language Models](https://mlsanity.com/paper/2410.03129/) (2024)
- [LittleBit: Ultra Low-Bit Quantization via Latent Factorization](https://mlsanity.com/paper/2506.13771/) (2025)
- [CRVQ: Channel-Relaxed Vector Quantization for Extreme Compression of LLMs](https://mlsanity.com/paper/2412.09282/) (2024)
- [Progressive Binarization with Semi-Structured Pruning for LLMs](https://mlsanity.com/paper/2502.01705/) (2025)
- [PT2-LLM: Post-Training Ternarization for Large Language Models](https://mlsanity.com/paper/2510.03267/) (2025)
- [HBLLM: Wavelet-Enhanced High-Fidelity 1-Bit Quantization for LLMs](https://mlsanity.com/paper/2512.00862/) (2025)
- [Enhancing Ultra-Low-Bit Quantization of Large Language Models Through Saliency-Aware Partial Retraining](https://mlsanity.com/paper/2504.13932/) (2025)
- [Highly Efficient and Effective LLMs with Multi-Boolean Architectures](https://mlsanity.com/paper/2505.22811/) (2025)
- [D2Quant: Accurate Low-bit Post-Training Weight Quantization for LLMs](https://mlsanity.com/paper/2602.02546/) (2026)
- [Rethinking 1-bit Optimization Leveraging Pre-trained Large Language Models](https://mlsanity.com/paper/2508.06974/) (2025)
- [NanoQuant: Efficient Sub-1-Bit Quantization of Large Language Models](https://mlsanity.com/paper/2602.06694/) (2026)
- [Evolutionary Feature-wise Thresholding for Binary Representation of NLP Embeddings](https://mlsanity.com/paper/2507.17025/) (2025)
- [RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs](https://mlsanity.com/paper/2602.05367/) (2026)

## Abstract (arXiv)

Binarization, which converts weight parameters to binary values, has emerged as an effective strategy to reduce the size of large language models (LLMs). However, typical binarization techniques significantly diminish linguistic effectiveness of LLMs. To address this issue, we introduce a novel binarization technique called Mixture of Scales (BinaryMoS). Unlike conventional methods, BinaryMoS employs multiple scaling experts for binary weights, dynamically merging these experts for each token to adaptively generate scaling factors. This token-adaptive approach boosts the representational power of binarized LLMs by enabling contextual adjustments to the values of binary weights. Moreover, because this adaptive process only involves the scaling factors rather than the entire weight matrix, BinaryMoS maintains compression efficiency similar to traditional static binarization methods. Our experimental results reveal that BinaryMoS surpasses conventional binarization techniques in various natural language processing tasks and even outperforms 2-bit quantization methods, all while maintaining similar model size to static binarization techniques.