R2Q: Residual Refinement Quantization for Robust 2-Bit Large Language Models
Its authors withdrew this paper, so there is no full text to read or summarize.
Lists
Only you see this
Abstract
The dramatic growth of Large Language Models (LLMs) has been accompanied by significant computational and memory demands, driving the adoption of low-bit quantization. While 8-bit and 4-bit formats have become standard, ultra-low-bit quantization, particularly 2-bit, presents a substantial challenge due to severe accuracy degradation. To address this, we propose Residual Refinement Quantization (R2Q)—a novel 2-bit quantization strategy that decomposes the quantization process into two sequential 1-bit subproblems, enabling adaptive quantization lattice. Extensive experiments on Llama, OPT and Qwen were conducted across diverse benchmarks, including question answering, commonsense reasoning, and language modeling. The results demonstrate that R2Q consistently outperforms state-of-the-art 2-bit quantization baselines in both coarse-grained and fine-grained settings. The refinement-based design of R2Q not only enhances quantization performance but also improves training stability and convergence under aggressive compression. Furthermore, R2Q is modular by design and can be seamlessly integrated into existing quantization-aware training (QAT) pipelines.
BibTeX
@misc{chen2026r,
author = {Jiayi Chen and Jieqi Shi and Jing Huo and Chen Wu},
title = {{R2Q: Residual Refinement Quantization for Robust 2-Bit Large Language Models}},
year = {2026},
url = {https://openreview.net/forum?id=YjMCArLE1r},
howpublished = {OpenReview},
note = {Submitted to ICLR 2026},
}