Follow the Rules: Reasoning for Video Anomaly Detection with Large Language Models
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Accepted at European Conference on Computer Vision (ECCV) 2024
AI 大模型
大模型数学、逻辑、规划、多步推理和测试时计算能力。
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Accepted at European Conference on Computer Vision (ECCV) 2024
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Extended abstract of arXiv:2305.16602 for CVPR EgoVis Workshop
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
Comments The paper is submitted to the IEEE conference
专题命中 逻辑推理 :reasoning(title,abstract)
Comments 25 Pages, 4 figures, 3 tables
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Accepted by NeurIPS 2023
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :planning(title,abstract)
Comments PhD thesis; also available at http://kth.diva-portal.org/smash/get/diva2:1427745/FULLTEXT01.pdf
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Extended version, version of record accepted at the 20th International Conference on Autonomous Agents and Multiagent Systems (AAMAS-21)
专题命中 逻辑推理 :planning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
Comments 36 pages; 10 Figures
Journal ref Philosophies 2020, 5(4), 25
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Published in BRACIS 2018
专题命中 逻辑推理 :reasoning(title,abstract)
Comments piblished on BRACIS 2017
专题命中 逻辑推理 :reasoning(title,abstract)
Comments In Proceedings TARK 2019, arXiv:1907.08335
Journal ref EPTCS 297, 2019, pp. 121-139
专题命中 逻辑推理 :reasoning(title,abstract)
Comments In Proceedings TARK 2019, arXiv:1907.08335
Journal ref EPTCS 297, 2019, pp. 106-120
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Accepted in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2019
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
Comments to be published in TOCL ACM journal
专题命中 逻辑推理 :reasoning(title,abstract)
Comments arXiv admin note: text overlap with arXiv:1112.6275, arXiv:1202.1309
Journal ref Logical Methods in Computer Science, Volume 13, Issue 1 (March 17, 2017) lmcs:3204
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Long version of paper accepted to appear at the 2019 Indian Conference on Logic and Applictaions
专题命中 逻辑推理 :reasoning(title,abstract)
Comments Presented at the 1st International Workshop on Argument for Agreement and Assurance (AAA 2013)
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
专题命中 逻辑推理 :reasoning(title,abstract)
Comments This paper is the full version of the article that is to appear in the ENTCS proceedings of the 25th conference on the Mathematical Foundations of Programming Semantics (MFPS), April 2009, University of Oxford
专题命中 逻辑推理 :reasoning(title,abstract)
Comments 32 pages
形式分析几何:一种基于神经符号的多模态解析几何问题生成框架
机构 * Xi’an Jiaotong-Liverpool University(西交利物浦大学)
专题命中 逻辑推理 :reasoning(abstract);math reasoning(abstract);verifier(abstract);分类 cs.AI
AI总结 研究解析几何问题生成,提出基于神经符号的FormalAnalyticGeo框架,利用CDL及四个大语言模型组件,无需人工注释自动生成问题,形成闭环,生成的AnalyticGeo7K数据集问题误差小,框架和数据集将公开。
DIVE:通过多样性驱动的技能进化解锁冻结语言模型的自我提升
专题命中 逻辑推理 :reasoning(abstract);logical reasoning(abstract);verifier(abstract);分类 cs.CL
AI总结 DIVE是一种多样性驱动的无参数框架,可让冻结LLM从任务经验和验证器反馈中进化出自然语言技能,在多项推理任务上优于现有方法,还能实现模型间技能迁移,让小模型性能匹配或超越大模型。
从暴力到语义洞察:基于LLM的性能引导数据转换设计
机构 * Computer Vision Lab, CAIDAS & IFI, University of Würzburg(计算机视觉实验室、CAIDAS与IFI、乌尔姆大学)
专题命中 逻辑推理 :chain-of-thought(abstract,abstract_cn);reasoning(abstract);分类 cs.LG
AI总结 本文提出了一种基于LLM的性能引导数据转换设计方法,通过经验反馈实现闭环优化,减少穷举搜索需求,提升代码生成的准确性与任务对齐性。