Input-Aware Sparse Attention for Real-Time Co-Speech Video Generation
机构 * Carnegie Mellon University(卡内基梅隆大学) ; PAII Inc.(PAII公司)
专题命中 扩散模型 :diffusion(abstract);分类 cs.CV
Comments Project Page: https://beijia11.github.io/IASA
视觉与机器人
图像生成、文生图、图像编辑、扩散模型和可控生成。
机构 * Carnegie Mellon University(卡内基梅隆大学) ; PAII Inc.(PAII公司)
专题命中 扩散模型 :diffusion(abstract);分类 cs.CV
Comments Project Page: https://beijia11.github.io/IASA
专题命中 扩散模型 :diffusion(abstract)
Comments accepted for publication in A&A
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
Comments 8 pages, 3 figures, 2 tables. ICRC 2025 conference procceeding
Journal ref PoS(ICRC2025)874
机构 * Department of Finance and Risk Engineering(金融与风险工程系) ; New York University(纽约大学) ; ETH Zurich(苏黎世联邦理工学院)
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
Comments 38 pages, 13 figures
专题命中 扩散模型 :diffusion(abstract)
Comments 18 pages, 1st version
机构 * State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences(数学科学国家重点实验室,数学与系统科学研究院,中国科学院) ; School of Mathematics Sciences, University of Chinese Academy of Sciences(中国科学院大学数学科学学院) ; Key Laboratory of Systems Health Science of Zhejiang Province, School of Life Science, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Chinese Academy of Sciences(浙江省系统健康科学重点实验室,生命科学学院,杭州高等研究院,中国科学院)
专题命中 扩散模型 :diffusion(abstract)
机构 * University of Chicago(芝加哥大学) ; J.P. Morgan AI Research(摩根大通AI研究) ; J.P. Morgan Quantitative Research(摩根大通量化研究)
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
Comments 48pages
机构 * Department of Computer and Information Science, University of Pennsylvania(计算机与信息科学系,宾夕法尼亚大学) ; Centre for Computational Biology, Duke-NUS Medical School, Singapore(计算生物学中心,新加坡国立大学医学学院) ; Department of Bioengineering, University of Pennsylvania(生物工程系,宾夕法尼亚大学)
专题命中 扩散模型 :diffusion(abstract)
专题命中 扩散模型 :diffusion(abstract)
Comments 10 pages, 2 figures
专题命中 扩散模型 :diffusion(abstract)
Comments 9 pages, 4 figures
专题命中 扩散模型 :diffusion(abstract)
机构 * IBM Research(IBM研究院) ; MIT(麻省理工学院) ; Georgia Tech(佐治亚理工学院) ; RPI(罗切斯特理工学院)
专题命中 扩散模型 :diffusion(abstract)
Comments Tutorial at ICML 2025
专题命中 扩散模型 :diffusion(abstract)
机构 * Vector Institute(向量研究所) ; Bosch-Delta Lab(博世-德尔塔实验室)
专题命中 扩散模型 :diffusion(abstract)
Comments 14 pages, 1 figure, and 9 tables; To be published in the Proceedings of the Forty-Second International Conference on Machine Learning
专题命中 扩散模型 :diffusion(abstract)
Journal ref Phys. Rev. A 111, 053507 (2025)
机构 * Cornell University(康奈尔大学)
专题命中 可控生成 :diffusion(title,abstract);image generation(title);分类 cs.CV
Comments First two listed authors have equal contribution. The latest version has been accepted to SIGGRAPH 2024
机构 * Institute for AI Industry Research (AIR), Tsinghua University(人工智能产业研究院(AIR),清华大学) ; Department of Computer Science and Technology, Tsinghua University(计算机科学与技术系,清华大学) ; Qiuzhen College, Tsinghua University(启真学院,清华大学)
专题命中 图像修复 :inpainting(abstract)
Comments This version (v2) includes minor edits. The paper has been accepted to NeurIPS 2025. Code is available at: https://github.com/MuZhao2333/MolFLAE
机构 * Sorbonne University(索邦大学) ; CNRS(法国国家科学研究中心) ; LIP6(LIP6研究所)
专题命中 个性化与一致性 :diffusion(abstract);分类 cs.CV
机构 * CyberAgent Tokyo Japan(CyberAgent东京日本)
专题命中 图像生成评测 :image editing(abstract);分类 cs.CV
Comments This is the author's version of the work. It is posted here for your personal use. Not for redistribution. The definitive Version of Record was published in Proceedings of the 33rd ACM International Conference on Multimedia (MM '25), October 27-31, 2025, Dublin, Ireland, https://doi.org/10.1145/3746027.3758297
专题命中 效率与蒸馏 :image generation(abstract);text-to-image(abstract);分类 cs.CV