arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

大模型推理能力

大模型数学、逻辑、规划、多步推理和测试时计算能力。

2025-07-24 至 2025-07-24 共收录 5 信号源:cs.CL, cs.AI, cs.LG

1. 其他推理 5 篇

2507.17477 2025-07-24 cs.AI 57%

An Uncertainty-Driven Adaptive Self-Alignment Framework for Large Language Models

Haoran Sun, Zekun Zhang, Shaoning Zeng

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2503.23956 2025-07-24 cs.CV cs.AI 57%

AirCache: Activating Inter-modal Relevancy KV Cache Compression for Efficient Large Vision-Language Model Inference

Kai Huang, Hao Zou, Bochen Wang, Ye Xi, Zhen Xie, Hao Wang

机构 * Alibaba Group(阿里巴巴集团)

专题命中 其他推理 :reasoning(abstract);分类 cs.AI

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17209 2025-07-24 cs.HC cs.LG 57%

HypoChainer: A Collaborative System Combining LLMs and Knowledge Graphs for Hypothesis-Driven Scientific Discovery

Haoran Jiang, Shaohan Shi, Yunjie Yao, Chang Jiang, Quan Li

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.17204 2025-07-24 cs.LG 57%

Filter-And-Refine: A MLLM Based Cascade System for Industrial-Scale Video Content Moderation

Zixuan Wang, Jinghao Shi, Hanzhong Liang, Xiang Shen, Vera Wen, Zhiqian Chen, Yifan Wu, Zhixin Zhang, Hongyu Xiong

机构 * TikTok(字节跳动)

专题命中 其他推理 :reasoning(abstract);分类 cs.LG

Comments Camera Ready for ACL 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2507.10054 2025-07-24 cs.SE 50%

Explicit Vulnerability Generation with LLMs: An Investigation Beyond Adversarial Attacks

Emir Bosnak, Sahand Moslemi, Mayasah Lami, Anil Koyuncu

专题命中 其他推理 :reasoning(abstract)

Comments Accepted to ICSME 2025

详情

展开后加载摘要…

URL PDF HTML 收藏