arXivDaily arXiv每日学术速递 周一至周五更新

大厂专区

Intel(英特尔)

2026-08-04 至 2026-08-04 共收录 2
2608.01078 2026-08-04 cs.CL cs.AI 新提交

Attend to Your Own Thoughts: Breaking the Barrier for Post-Training Quantization of Reasoning LLMs through the Lens of 1.58-Bit Quantization

关注自身思维:通过1.58比特量化视角打破推理型大语言模型的后训练量化障碍

Shigeng Wang, Chao Li, Yangyuxuan Kang, Jiawei Fan, Anbang Yao

机构 * Intel Labs China(英特尔中国实验室)

AI总结 该研究提出ScaleQ-1.58三值后训练量化框架,通过集成AYOT校准方法,提升推理型LLM量化性能,该框架可扩展且泛化性强,仅需少量校准token即可实现优异效果。

Comments This research work was completed and submitted for publication in early May 2026. The project page: https://github.com/IntelChina-AI/BitTern

详情

展开后加载摘要…

URL PDF HTML 收藏
2607.17508 2026-08-04 cs.LG cs.AI 版本更新

Retrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Healthcare

检索增强可解释学习:迈向医疗保健领域特定任务的零样本模型

Sazan Mahbub, Caleb Ellington, Zhiyuan Li, Yixin Yang, Souvik Kundu, Ben Lengerich, Eric P. Xing

机构 * Carnegie Mellon University(卡内基梅隆大学) University of Wisconsin–Madison(威斯康星大学麦迪逊分校) Mohamed bin Zayed University of AI(穆罕默德·本·扎耶德人工智能大学) GenBio AI(基因生物人工智能公司) Intel(英特尔公司)

AI总结 研究针对医疗保健领域特定任务零样本模型问题推出检索增强可解释学习(RAIL)框架,通过检索相关任务并传递结构生成新预测器,概率公式提供不确定性支持可靠性感知部署,在临床程序预测任务中性能可靠,还提升模型透明度。

Comments A preliminary, non-archival version of this work, titled RAG-IM, was presented at NeurIPS 2024 workshops and the ML4H 2024 Findings track. The work was subsequently renamed Retrieval-Augmented Interpretable Learning (RAIL)

详情

展开后加载摘要…

URL PDF HTML 收藏