{"type":"ScholarlyArticle","title":"OJBKQ: Objective-Joint Babai-Klein Quantization","authors":[{"name":"Xinyu Wang","slug":"xinyu-wang","given":"Xinyu","family":"Wang","affiliation":""},{"name":"Ziyu Zhao","slug":"ziyu-zhao","given":"Ziyu","family":"Zhao","affiliation":""},{"name":"Peng Lu","slug":"peng-lu","given":"Peng","family":"Lu","affiliation":""},{"name":"Yu Gu","slug":"yu-gu","given":"Yu","family":"Gu","affiliation":""},{"name":"Xiao-Wen Chang","slug":"xiao-wen-chang","given":"Xiao-Wen","family":"Chang","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/264","url":"https://ijcai.org/proceedings/2026/264","pdf":"https://ijcai.org/proceedings/2026/0264.pdf","markdown":"https://ijcai.org/proceedings/2026/264.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/264","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Constraint Satisfaction and Optimization","track":"Main Track","number":264,"pages":{"first":2373,"last":2381},"keywords":["Constraint Satisfaction and Optimization: Constraint optimization problems","Natural Language Processing: Language models"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}