{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T10:13:00Z","timestamp":1793527980656,"version":"4.5.0"},"publisher-location":"Cham","reference-count":124,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726637","type":"print"},{"value":"9783031726644","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-72664-4_9","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T13:02:04Z","timestamp":1729861324000},"page":"148-166","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":109,"title":["ZigMa: A DiT-style Zigzag Mamba Diffusion Model"],"prefix":"10.1007","author":[{"given":"Vincent Tao","family":"Hu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefan Andreas","family":"Baumann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Gui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Olga","family":"Grebenkova","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pingchuan","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Fischer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn","family":"Ommer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"9_CR1","unstructured":"Agarwal, N., Suo, D., Chen, X., Hazan, E.: Spectral state space models. arXiv (2023)"},{"key":"9_CR2","unstructured":"Ahamed, M.A., Cheng, Q.: Mambatab: a simple yet effective approach for handling tabular data. arXiv (2024)"},{"key":"9_CR3","unstructured":"Albergo, M.S., Boffi, N.M., Vanden-Eijnden, E.: Stochastic interpolants: a unifying framework for flows and diffusions. arXiv (2023)"},{"key":"9_CR4","unstructured":"Albergo, M.S., Vanden-Eijnden, E.: Building normalizing flows with stochastic interpolants. arXiv (2022)"},{"key":"9_CR5","unstructured":"Ali, A., Zimerman, I., Wolf, L.: The hidden attention of mamba models. arXiv (2024)"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Anderson, B.D.: Reverse-time diffusion equation models. In: Stochastic Processes and their Applications (1982)","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"9_CR7","unstructured":"Anthony, Q., Tokpanov, Y., Glorioso, P., Millidge, B.: Blackmamba: mixture of experts for state-space models. arXiv (2024)"},{"key":"9_CR8","unstructured":"Ao, S., et al.: Burstattention: an efficient distributed attention framework for extremely long sequences. arXiv (2024)"},{"key":"9_CR9","doi-asserted-by":"crossref","unstructured":"Bao, F., Li, C., Cao, Y., Zhu, J.: All are worth words: a vit backbone for score-based diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"9_CR10","unstructured":"Bao, F., et al.: One transformer fits all distributions in multi-modal diffusion at scale. arXiv (2023)"},{"key":"9_CR11","unstructured":"Beck, M., et al.: xlstm: extended long short-term memory (2024)"},{"key":"9_CR12","doi-asserted-by":"crossref","unstructured":"Behrouz, A., Hashemi, F.: Graph mamba: towards learning on graphs with state space models. arXiv (2024)","DOI":"10.1145\/3637528.3672044"},{"key":"9_CR13","unstructured":"Beltagy, I., Peters, M.E., Cohan, A.: Longformer: the long-document transformer. arXiv (2020)"},{"key":"9_CR14","unstructured":"Ben-Hamu, H., et al.: Matching normalizing flows and probability paths on manifolds. In: ICML (2022)"},{"key":"9_CR15","unstructured":"Brandon, W., et al.: Striped attention: faster ring attention for causal transformers. arXiv preprint arXiv:2311.09431 (2023)"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"9_CR17","unstructured":"Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.K.: Neural ordinary differential equations. In: NeurIPS (2018)"},{"key":"9_CR18","unstructured":"Chen, S., et al.: Gentron: delving deep into diffusion transformers for image and video generation. arXiv (2023)"},{"key":"9_CR19","unstructured":"Child, R., Gray, S., Radford, A., Sutskever, I.: Generating long sequences with sparse transformers. arXiv (2019)"},{"key":"9_CR20","unstructured":"Choromanski, K., et\u00a0al.: Rethinking attention with performers. arXiv (2020)"},{"key":"9_CR21","unstructured":"Crowson, K., Baumann, S.A., Birch, A., Abraham, T.M., Kaplan, D.Z., Shippole, E.: Scalable high-resolution pixel-space image synthesis with hourglass diffusion transformers. arXiv (2024)"},{"key":"9_CR22","unstructured":"Dao, Q., Phung, H., Nguyen, B., Tran, A.: Flow matching in latent space. arXiv (2023)"},{"key":"9_CR23","unstructured":"Dao, T., Fu, D., Ermon, S., Rudra, A., R\u00e9, C.: Flashattention: fast and memory-efficient exact attention with io-awareness. In: NeurIPS (2022)"},{"key":"9_CR24","unstructured":"Dehghani, M., et\u00a0al.: Scaling vision transformers to 22 billion parameters. In: ICML (2023)"},{"key":"9_CR25","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"9_CR27","unstructured":"Fei, Z., Fan, M., Yu, C., Huang, J.: Scalable diffusion models with state space backbone. arXiv (2024)"},{"key":"9_CR28","unstructured":"Fischer, J.S., Gui, M., Ma, P., Stracke, N., Baumann, S.A., Ommer, B.: Boosting latent diffusion with flow matching. In: ECCV (2024)"},{"key":"9_CR29","unstructured":"Fu, D.Y., Dao, T., Saab, K.K., Thomas, A.W., Rudra, A., R\u00e9, C.: Hungry hungry hippos: towards language modeling with state space models. arXiv (2022)"},{"key":"9_CR30","unstructured":"Fuest, M., Ma, P., Gui, M., Fischer, J.S., Hu, V.T., Ommer, B.: Diffusion models and representation learning: a survey. arXiv preprint arXiv:2407.00783 (2024)"},{"key":"9_CR31","unstructured":"Gong, H., Kang, L., Wang, Y., Wan, X., Li, H.: nnmamba: 3d biomedical image segmentation, classification and landmark detection with state space model. arXiv (2024)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Gong, J., Foo, L.G., Fan, Z., Ke, Q., Rahmani, H., Liu, J.: Diffpose: toward more reliable 3d pose estimation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"9_CR33","unstructured":"Gu, A., Dao, T.: Mamba: linear-time sequence modeling with selective state spaces. In: CoLM (2024)"},{"key":"9_CR34","unstructured":"Gu, A., Goel, K., Gupta, A., R\u00e9, C.: On the parameterization and initialization of diagonal state space models. In: NeurIPS (2022)"},{"key":"9_CR35","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces (2021)"},{"key":"9_CR36","unstructured":"Gu, A., et al.: Combining recurrent, convolutional, and continuous-time models with linear state space layers. In: NeurIPS (2021)"},{"key":"9_CR37","unstructured":"Gui, M., et al.: Depthfm: fast monocular depth estimation with flow matching. arXiv preprint arXiv:2403.13788 (2024)"},{"key":"9_CR38","doi-asserted-by":"crossref","unstructured":"Guo, H., Li, J., Dai, T., Ouyang, Z., Ren, X., Xia, S.T.: Mambair: a simple baseline for image restoration with state-space model. arXiv (2024)","DOI":"10.1007\/978-3-031-72649-1_13"},{"key":"9_CR39","unstructured":"Gupta, A., Gu, A., Berant, J.: Diagonal state spaces are as effective as structured state spaces. In: NeurIPS (2022)"},{"key":"9_CR40","unstructured":"He, W., et al.: Densemamba: state space models with dense hidden connection for efficient large language models. arXiv (2024)"},{"key":"9_CR41","doi-asserted-by":"crossref","unstructured":"He, X., et al.: Pan-mamba: effective pan-sharpening with state space model. arXiv (2024)","DOI":"10.1016\/j.inffus.2024.102779"},{"key":"9_CR42","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-Or, D.: Prompt-to-prompt image editing with cross attention control. arXiv (2022)"},{"key":"9_CR43","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS (2020)"},{"key":"9_CR44","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. In: ARXIV (2022)"},{"key":"9_CR45","doi-asserted-by":"crossref","unstructured":"Hu, V.T., Chen, Y., Caron, M., Asano, Y.M., Snoek, C.G., Ommer, B.: Guided diffusion from self-supervised diffusion features. In: ARXIV (2023)","DOI":"10.1109\/CVPR52729.2023.01766"},{"key":"9_CR46","unstructured":"Hu, V.T., et al.: Flow matching for conditional text generation in a few sampling steps, pp. 380\u2013392 (2024)"},{"key":"9_CR47","unstructured":"Hu, V.T., et al.: Motion flow matching for human motion synthesis and editing. In: ARXIV (2023)"},{"key":"9_CR48","doi-asserted-by":"crossref","unstructured":"Hu, V.T., Zhang, D.W., Asano, Y.M., Burghouts, G.J., Snoek, C.G.M.: Self-guided diffusion models. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01766"},{"key":"9_CR49","unstructured":"Hu, V.T., Zhang, D.W., Mettes, P., Tang, M., Zhao, D., Snoek, C.G.: Latent space editing in transformer-based flow matching. In: ICML 2023 Workshop, New Frontiers in Learning, Control, and Dynamical Systems (2023)"},{"key":"9_CR50","unstructured":"Huang, Z., Zhou, P., Yan, S., Lin, L.: Scalelong: towards more stable training of diffusion model via scaling network long skip connection. In: NeurIPS (2024)"},{"key":"9_CR51","unstructured":"Huang, Z., Ben, Y., Luo, G., Cheng, P., Yu, G., Fu, B.: Shuffle transformer: rethinking spatial shuffle for vision transformer. arXiv preprint arXiv:2106.03650 (2021)"},{"key":"9_CR52","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: NeurIPS (2022)"},{"key":"9_CR53","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"9_CR54","unstructured":"Kingma, D., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. In: NeurIPS (2021)"},{"key":"9_CR55","unstructured":"Kingma, D.P., Gao, R.: Understanding the diffusion objective as a weighted integral of elbos. arXiv (2023)"},{"key":"9_CR56","unstructured":"Kitaev, N., Kaiser, \u0141., Levskaya, A.: Reformer: the efficient transformer. arXiv (2020)"},{"key":"9_CR57","unstructured":"Lee, S., Kim, B., Ye, J.C.: Minimizing trajectory curvature of ode-based generative models. In: ICML (2023)"},{"key":"9_CR58","doi-asserted-by":"crossref","unstructured":"Li, K., et al.: Videomamba: state space model for efficient video understanding. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"9_CR59","doi-asserted-by":"crossref","unstructured":"Li, S., Singh, H., Grover, A.: Mamba-nd: selective state space modeling for multi-dimensional data. arXiv (2024)","DOI":"10.1007\/978-3-031-73414-4_5"},{"key":"9_CR60","unstructured":"Li, Y., Bornschein, J., Chen, T.: Denoising autoregressive representation learning. arXiv preprint arXiv:2403.05196 (2024)"},{"key":"9_CR61","unstructured":"Liang, D., et al.: Pointmamba: a simple state space model for point cloud analysis. arXiv preprint arXiv:2402.10739 (2024)"},{"key":"9_CR62","unstructured":"Lin, B., Jiang, W., Chen, P., Zhang, Y., Liu, S., Chen, Y.C.: Mtmamba: enhancing multi-task dense scene understanding by mamba-based decoders. In: ECCV (2024)"},{"key":"9_CR63","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"9_CR64","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: ICLR (2023)"},{"key":"9_CR65","unstructured":"Liu, G.H., Chen, T., So, O., Theodorou, E.: Deep generalized schr\u00f6dinger bridge. In: NeurIPS (2022)"},{"key":"9_CR66","unstructured":"Liu, H., Zaharia, M., Abbeel, P.: Ring attention with blockwise transformers for near-infinite context. arXiv (2023)"},{"key":"9_CR67","doi-asserted-by":"crossref","unstructured":"Liu, J., et\u00a0al.: Swin-umamba: mamba-based unet with imagenet-based pretraining. arXiv (2024)","DOI":"10.1007\/978-3-031-72114-4_59"},{"key":"9_CR68","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. arXiv (2022)"},{"key":"9_CR69","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow. In: ICLR (2023)"},{"key":"9_CR70","unstructured":"Liu, Y., et al.: Vmamba: visual state space model. arXiv (2024)"},{"key":"9_CR71","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"9_CR72","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"9_CR73","unstructured":"Ma, J., Li, F., Wang, B.: U-mamba: enhancing long-range dependency for biomedical image segmentation. arXiv (2024)"},{"key":"9_CR74","doi-asserted-by":"crossref","unstructured":"Ma, N., Goldstein, M., Albergo, M.S., Boffi, N.M., Vanden-Eijnden, E., Xie, S.: Sit: exploring flow and diffusion-based generative models with scalable interpolant transformers. arXiv (2024)","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"9_CR75","unstructured":"McKenna, D.M.: Hilbert curves: Outside-in and inside-gone. Mathemaesthetics, Inc. (2019)"},{"key":"9_CR76","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"9_CR77","unstructured":"Nguyen, E., et al.: S4nd: modeling images and videos as multidimensional signals with state spaces. In: NeurIPS (2022)"},{"key":"9_CR78","unstructured":"OpenAI: Sora: Creating video from text (2024). https:\/\/openai.com\/sora"},{"key":"9_CR79","doi-asserted-by":"crossref","unstructured":"Park, J., Kim, H.S., Ko, K., Kim, M., Kim, C.: Videomamba: spatio-temporal selective state space model. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72698-9_1"},{"key":"9_CR80","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. arXiv (2022)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"9_CR81","unstructured":"Peng, B., et\u00a0al.: Eagle and finch: rwkv with matrix-valued states and dynamic recurrence. arXiv preprint arXiv:2404.05892 (2024)"},{"key":"9_CR82","unstructured":"Qin, Z., et al.: Hgrn2: gated linear rnns with state expansion. arXiv preprint arXiv:2404.07904 (2024)"},{"key":"9_CR83","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"9_CR84","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"9_CR85","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"9_CR86","unstructured":"Ruan, J., Xiang, S.: Vm-unet: vision mamba unet for medical image segmentation. arXiv (2024)"},{"key":"9_CR87","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Sotnikov, G., Elhoseiny, M.: Aligning latent and image spaces to connect the unconnectable. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01388"},{"key":"9_CR88","unstructured":"Smith, J.T., Warrington, A., Linderman, S.W.: Simplified state space layers for sequence modeling. arXiv (2022)"},{"key":"9_CR89","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"9_CR90","unstructured":"Song, Y., Ermon, S.: Generative modeling by estimating gradients of the data distribution. arXiv (2019)"},{"key":"9_CR91","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"9_CR92","unstructured":"Stein, G., et al.: Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models. In: NeurIPS (2023)"},{"key":"9_CR93","unstructured":"Sun, Z., Yang, Y., Yoo, S.: Sparse attention with learning to hash. In: ICLR (2021)"},{"key":"9_CR94","doi-asserted-by":"crossref","unstructured":"Tang, R., et al.: What the daam: interpreting stable diffusion using cross attention. arXiv (2022)","DOI":"10.18653\/v1\/2023.acl-long.310"},{"key":"9_CR95","unstructured":"Tikochinski, R., Goldstein, A., Meiri, Y., Hasson, U., Reichart, R.: An incremental large language model for long text processing in the brain (2024)"},{"key":"9_CR96","unstructured":"Tong, A., et al.: Simulation-free schr $$\\backslash $$\" odinger bridges via score and flow matching. arXiv (2023)"},{"key":"9_CR97","unstructured":"Unterthiner, T., van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: FVD: a new metric for video generation. In: ICLR Workshop (2019)"},{"key":"9_CR98","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"9_CR99","unstructured":"Wang, C., Tsepa, O., Ma, J., Wang, B.: Graph-mamba: towards long-range graph sequence modeling with selective state spaces. arXiv (2024)"},{"key":"9_CR100","unstructured":"Wang, J., Gangavarapu, T., Yan, J.N., Rush, A.M.: Mambabyte: token-free selective state space model. arXiv (2024)"},{"key":"9_CR101","doi-asserted-by":"crossref","unstructured":"Wang, J., Yan, J.N., Gu, A., Rush, A.M.: Pretraining without attention. arXiv (2022)","DOI":"10.18653\/v1\/2023.findings-emnlp.5"},{"key":"9_CR102","unstructured":"Wang, S., Li, Q.: Stablessm: alleviating the curse of memory in state-space models through stable reparameterization. arXiv (2023)"},{"key":"9_CR103","unstructured":"Wang, S., Xue, B.: State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory. In: NeurIPS (2024)"},{"key":"9_CR104","unstructured":"Wang, W., Ma, S., Xu, H., Usuyama, N., Ding, J., Poon, H., Wei, F.: When an image is worth 1,024 $$\\times $$ 1,024 words: a case study in computational pathology. arXiv (2023)"},{"key":"9_CR105","unstructured":"Wang, X., et al.: State space model for new-generation network alternative to transformers: a survey (2024)"},{"key":"9_CR106","unstructured":"Wang, X., Kang, Z., Mu, Y.: Text-controlled motion mamba: text-instructed temporal grounding of human motion. arXiv preprint arXiv:2404.11375 (2024)"},{"key":"9_CR107","unstructured":"Wang, Z., Ma, C.: Semi-mamba-unet: pixel-level contrastive cross-supervised visual mamba-based unet for semi-supervised medical image segmentation. arXiv (2024)"},{"key":"9_CR108","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zheng, J.Q., Zhang, Y., Cui, G., Li, L.: Mamba-unet: unet-like pure visual mamba for medical image segmentation. arXiv (2024)","DOI":"10.1109\/AINIT61980.2024.10581519"},{"key":"9_CR109","doi-asserted-by":"crossref","unstructured":"Wu, L., et al.: Fast point cloud generation with straight flows. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00911"},{"key":"9_CR110","doi-asserted-by":"crossref","unstructured":"Xia, W., Yang, Y., Xue, J.H., Wu, B.: Tedigan: text-guided diverse face image generation and manipulation. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"9_CR111","doi-asserted-by":"crossref","unstructured":"Xing, Z., Ye, T., Yang, Y., Liu, G., Zhu, L.: Segmamba: long-range sequential modeling mamba for 3d medical image segmentation. arXiv (2024)","DOI":"10.1007\/978-3-031-72111-3_54"},{"key":"9_CR112","doi-asserted-by":"crossref","unstructured":"Yan, J.N., Gu, J., Rush, A.M.: Diffusion models without attention. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"9_CR113","unstructured":"Yang, S., Wang, B., Shen, Y., Panda, R., Kim, Y.: Gated linear attention transformers with hardware-efficient training. In: ICML (2024)"},{"key":"9_CR114","unstructured":"Yang, S., Zhang, Y.: Fla: a triton-based library for hardware-efficient implementations of linear attention mechanism (2024). https:\/\/github.com\/sustcsonglin\/flash-linear-attention"},{"key":"9_CR115","unstructured":"Yang, Y., Xing, Z., Zhu, L.: Vivim: a video vision mamba for medical video object segmentation. arXiv (2024)"},{"key":"9_CR116","unstructured":"Yu, A., Nigmetov, A., Morozov, D., Mahoney, M.W., Erichson, N.B.: Robustifying state-space models for long sequences via approximate diagonalization. arXiv (2023)"},{"key":"9_CR117","doi-asserted-by":"crossref","unstructured":"Yu, S., Sohn, K., Kim, S., Shin, J.: Video probabilistic diffusion models in projected latent space. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"9_CR118","unstructured":"Zhang, T., Li, X., Yuan, H., Ji, S., Yan, S.: Point could mamba: point cloud learning via state space model. arXiv (2024)"},{"key":"9_CR119","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhou, X., Lin, M., Sun, J.: Shufflenet: an extremely efficient convolutional neural network for mobile devices. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00716"},{"key":"9_CR120","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liu, A., Reid, I., Hartley, R., Zhuang, B., Tang, H.: Motion mamba: efficient and long sequence motion generation with hierarchical and bidirectional selective ssm. In: ECCV (2024)","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"9_CR121","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Liu, A., Reid, I., Hartley, R., Zhuang, B., Tang, H.: Motion mamba: efficient and long sequence motion generation with hierarchical and bidirectional selective ssm. arXiv (2024)","DOI":"10.1007\/978-3-031-73232-4_15"},{"key":"9_CR122","unstructured":"Zheng, Z., Wu, C.: U-shaped vision mamba for single image dehazing. arXiv (2024)"},{"key":"9_CR123","unstructured":"Zhu, L., Liao, B., Zhang, Q., Wang, X., Liu, W., Wang, X.: Vision mamba: efficient visual representation learning with bidirectional state space model. In: ICML (2024)"},{"key":"9_CR124","unstructured":"zhuzilin: Ring flash attention (2024). https:\/\/github.com\/zhuzilin\/ring-flash-attention"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72664-4_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T03:32:51Z","timestamp":1732937571000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72664-4_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726637","9783031726644"],"references-count":124,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72664-4_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}