Proceedings

OJBKQ: Objective-Joint Babai-Klein Quantization

Xinyu Wang, Ziyu Zhao, Peng Lu, Yu Gu, Xiao-Wen Chang

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Main Track. Pages 2373-2381.

https://doi.org/10.24963/ijcai.2026/264

Keywords

  • Constraint Satisfaction and Optimization: Constraint optimization problems
  • Natural Language Processing: Language models

Abstract

Post-training quantization (PTQ) is widely used to compress large language models without retraining. However, many existing weight-only methods rely on heuristic objectives and greedy rounding strategies, leading to noticeable degradation under low-bit quantization. We propose OJBKQ, a layer-wise PTQ method that formulates weight quantization as a joint optimization problem over activations and weights, yielding a multiple-right-hand-side box-constrained integer least squares (BILS) problem per layer. To solve this NP-hard problem, we extend Klein’s randomized variant of Babai’s nearest-plane algorithm to handle box constraints and run the extended algorithm K times to generate K box-constrained Klein points. The minimum-residual candidate among these points and the box-constrained Babai point is selected as a suboptimal solution. Experiments on large language models show that OJBKQ achieves lower perplexity at 3–4 bits than existing PTQ methods, while maintaining comparable computational cost.

Xinyu Wang, Ziyu Zhao, Peng Lu, Yu Gu, and Xiao-Wen Chang. 2026. OJBKQ: Objective-Joint Babai-Klein Quantization. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 2373–2381. https://doi.org/10.24963/ijcai.2026/264
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards