{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:22:33Z","timestamp":1789467753573,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373137","type":"print"},{"value":"9783032373144","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37314-4_8","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:50:09Z","timestamp":1789462209000},"page":"129-149","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Your Data Manifold Is Secretly a\u00a0Reward Model: Shell-LCC for\u00a0Text-to-Video Generation"],"prefix":"10.1007","author":[{"given":"Shihao","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunzhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuguang","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junzhe","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"key":"8_CR1","unstructured":"Arvanitidis, G., Hansen, L.K., Hauberg, S.: Latent Space Oddity: On the Curvature of Deep Generative Models (2017). arXiv:1710.11379 arXiv preprint"},{"key":"8_CR2","unstructured":"Bansal, H., Lin, Z., Xie, T., Zong, Z., Yarom, M., Bitton, Y., Jiang, C., Sun, Y., Chang, K.W., Grover, A.: Videophy: Evaluating Physical Commonsense for Video Generation (2024). arXiv:2406.03520 arXiv preprint"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Bar-Tal, O., Chefer, H., Tov, O., Herrmann, C., Paiss, R., Zada, S., Ephrat, A., Hur, J., Liu, G., Raj, A.: Lumiere: a space-time diffusion model for video generation. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311. (2024)","DOI":"10.1145\/3680528.3687614"},{"issue":"6","key":"8_CR4","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1162\/089976603321780317","volume":"15","author":"M Belkin","year":"2003","unstructured":"Belkin, M., Niyogi, P.: Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput. 15(6), 1373\u20131396 (2003)","journal-title":"Neural Comput."},{"key":"8_CR5","unstructured":"Blattmann, A., Dockhorn, T., Kulal, S., Mendelevitch, D., Kilian, M., Lorenz, D., Levi, Y., English, Z., Voleti, V., Letts, A.: Stable video diffusion: Scaling latent video diffusion models to large datasets, (2023). arXiv:2311.15127 arXiv preprint"},{"issue":"8","key":"8_CR6","first-page":"1","volume":"1","author":"T Brooks","year":"2024","unstructured":"Brooks, T., Peebles, B., Holmes, C., DePue, W., Guo, Y., Jing, L., Schnurr, D., Taylor, J., Luhman, T., Luhman, E., et al.: Video generation models as world simulators. OpenAI Blog 1(8), 1 (2024)","journal-title":"OpenAI Blog"},{"key":"8_CR7","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems, p. 30. (2017)"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Dai, M., Hang, H.: Manifold matching via deep metric learning for generative modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6587\u20136597. (2021)","DOI":"10.1109\/ICCV48922.2021.00652"},{"key":"8_CR9","doi-asserted-by":"publisher","first-page":"2406","DOI":"10.52202\/068431-0175","volume":"35","author":"V De Bortoli","year":"2022","unstructured":"De Bortoli, V., Mathieu, E., Hutchinson, M., Thornton, J., Teh, Y.W., Doucet, A.: Riemannian score-based generative modelling. Adv. Neural. Inf. Process. Syst. 35, 2406\u20132422 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR10","unstructured":"Esser, P., Kulal, S., Blattmann, A., Entezari, R., M\u00fcller, J., Saini, H., Levi, Y., Lorenz, D., Sauer, A., Boesel, F.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"8_CR11","doi-asserted-by":"publisher","first-page":"79858","DOI":"10.52202\/075280-3497","volume":"36","author":"Y Fan","year":"2023","unstructured":"Fan, Y., Watkins, O., Du, Y., Liu, H., Ryu, M., Boutilier, C., Abbeel, P., Ghavamzadeh, M., Lee, K., Lee, K.: Dpok: Reinforcement learning for fine-tuning text-to-image diffusion models. Adv. Neural. Inf. Process. Syst. 36, 79858\u201379885 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Han, H., Li, S., Chen, J., Yuan, Y., Wu, Y., Deng, Y., Leong, C.T., Du, H., Fu, J., Li, Y., et\u00a0al.: Video-bench: human-aligned video generation benchmark. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 18858\u201318868 (2025)","DOI":"10.1109\/CVPR52734.2025.01757"},{"key":"8_CR13","doi-asserted-by":"publisher","first-page":"8633","DOI":"10.52202\/068431-0628","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR14","doi-asserted-by":"crossref","unstructured":"Huang, Z., He, Y., Yu, J., Zhang, F., Si, C., Jiang, Y., Zhang, Y., Wu, T., Jin, Q., Chanpaisit, N., et\u00a0al.: Vbench: comprehensive benchmark suite for video generative models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"8_CR15","unstructured":"Humayun, A.I., Amara, I., Schumann, C., Farnadi, G., Rostamzadeh, N., Havaei, M.: On the local geometry of deep generative manifolds. In: ICML 2024 Workshop on Geometry-grounded Representation Learning and Generative Modeling (2024)"},{"key":"8_CR16","unstructured":"Humayun, A.I., Amara, I., Vasconcelos, C., Ramachandran, D., Schumann, C., He, J., Heller, K., Farnadi, G., Rostamzadeh, N., Havaei, M.: What secrets do your manifolds hold? Understanding the local geometry of generative models. arXiv preprint arXiv:2408.08307 (2024)"},{"key":"8_CR17","unstructured":"Kondratyuk, D., Yu, L., Gu, X., Lezama, J., Huang, J., Schindler, G., Hornung, R., Birodkar, V., Yan, J., Chiu, M.C.: Videopoet: A Large Language Model for Zero-Shot Video Generation (2023). arXiv:2312.14125 arXiv preprint"},{"key":"8_CR18","unstructured":"Lee, K., Liu, H., Ryu, M., Watkins, O., Du, Y., Boutilier, C., Abbeel, P., Ghavamzadeh, M., Gu, S.S.: Aligning Text-to-Image Models Using Human Feedback (2023). arXiv:2302.12192 arXiv preprint"},{"key":"8_CR19","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow Matching for Generative Modeling (2022). arXiv:2210.02747 arXiv preprint"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, G., Liang, J., Li, Y., Liu, J., Wang, X., Wan, P., Zhang, D., Ouyang, W.: Flow-grpo: Training Flow Matching Models via Online RL (2025). arXiv preprint arXiv:2505.05470","DOI":"10.52202\/085713-1362"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Liu, J., Liu, G., Liang, J., Yuan, Z., Liu, X., Zheng, M., Wu, X., Wang, Q., Qin, W., Xia, M., Wang, X., Liu, X., Yang, F., Wan, P., Zhang, D., Gai, K., Yang, Y., Ouyang, W.: Improving Video Generation with Human Feedback (2025). arXiv preprint arXiv:2501.13918","DOI":"10.52202\/085713-2750"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, H., Zheng, Z., Wei, C., He, Y., Pi, R., Chen, Q.: Videodpo: omni-preference alignment for video diffusion generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8009\u20138019 (2025)","DOI":"10.1109\/CVPR52734.2025.00750"},{"key":"8_CR23","unstructured":"Liu, X., Gong, C., Liu, Q.: Flow straight and fast: learning to generate and transfer data with rectified flow (2022). arXiv preprint arXiv:2209.03003"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Liu, Y., Cun, X., Liu, X., Wang, X., Zhang, Y., Chen, H., Liu, Y., Zeng, T., Chan, R., Shan, Y.: Evalcrafter: benchmarking and evaluating large video generation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22139\u201322149 (2024)","DOI":"10.1109\/CVPR52733.2024.02090"},{"key":"8_CR25","unstructured":"Ma, X., Wang, Y., Chen, X., Jia, G., Liu, Z., Li, Y.F., Chen, C., Qiao, Y.: Latte: Latent Diffusion Transformer for Video Generation (2024). arXiv preprint arXiv:2401.03048"},{"key":"8_CR26","unstructured":"Munos, R., Valko, M., Calandriello, D., Azar, M.G., Rowland, M., Guo, Z.D., Tang, Y., Geist, M., Mesnard, T., Fiegel, C.: Nash learning from human feedback. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Ni, Y., Koniusz, P., Hartley, R., Nock, R.: Manifold learning benefits GANS. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11265\u201311274. (2022)","DOI":"10.1109\/CVPR52688.2022.01098"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205. (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"8_CR29","doi-asserted-by":"publisher","first-page":"53728","DOI":"10.52202\/075280-2338","volume":"36","author":"R Rafailov","year":"2023","unstructured":"Rafailov, R., Sharma, A., Mitchell, E., Manning, C.D., Ermon, S., Finn, C.: Direct preference optimization: your language model is secretly a reward model. Adv. Neural. Inf. Process. Syst. 36, 53728\u201353741 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Roweis, S.T., Saul, L.K.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323\u20132326 (2000)","DOI":"10.1126\/science.290.5500.2323"},{"key":"8_CR31","unstructured":"Saul, L.K., Roweis, S.T.: Think globally, fit locally: unsupervised learning of low dimensional manifolds. J. Mach. Learn. Res. 4, 119\u2013155 (2003)"},{"key":"8_CR32","unstructured":"Singer, U., Polyak, A., Hayes, T., Yin, X., An, J., Zhang, S., Hu, Q., Yang, H., Ashual, O., Gafni, O.: Make-a-Video: Text-to-Video Generation Without Text-Video Data (2022). arXiv:2209.14792 arXiv preprint"},{"key":"8_CR33","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-Based Generative Modeling Through Stochastic Differential Equations (2020). arXiv:2011.13456 arXiv preprint"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Sun, K., Huang, K., Liu, X., Wu, Y., Xu, Z., Li, Z., Liu, X.: T2v-compbench: a comprehensive benchmark for compositional text-to-video generation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 8406\u20138416 (2025)","DOI":"10.1109\/CVPR52734.2025.00787"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Tenenbaum, J.B., Silva, V.D., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319\u20132323 (2000)","DOI":"10.1126\/science.290.5500.2319"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Vershynin, R.: High-dimensional Probability: An Introduction with Applications in Data Science, vol. 47. Cambridge University Press (2018)","DOI":"10.1017\/9781108231596"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Wallace, B., Dang, M., Rafailov, R., Zhou, L., Lou, A., Purushwalkam, S., Ermon, S., Xiong, C., Joty, S., Naik, N.: Diffusion model alignment using direct preference optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8228\u20138238. (2024)","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"8_CR38","unstructured":"Wan, T., Wang, A., Ai, B., Wen, B., Mao, C., Xie, C.W., Chen, D., Yu, F., Zhao, H., Yang, J., Zeng, J., Wang, J., Zhang, J., Zhou, J., Wang, J., Chen, J., Zhu, K., Zhao, K., Yan, K., Huang, L., Feng, M., Zhang, N., Li, P., Wu, P., Chu, R., Feng, R., Zhang, S., Sun, S., Fang, T., Wang, T., Gui, T., Weng, T., Shen, T., Lin, W., Wang, W., Wang, W., Zhou, W., Wang, W., Shen, W., Yu, W., Shi, X., Huang, X., Xu, X., Kou, Y., Lv, Y., Li, Y., Liu, Y., Wang, Y., Zhang, Y., Huang, Y., Li, Y., Wu, Y., Liu, Y., Pan, Y., Zheng, Y., Hong, Y., Shi, Y., Feng, Y., Jiang, Z., Han, Z., Wu, Z.F., Liu, Z.: Wan: Open and Advanced Large-Scale Video Generative Models (2025). arXiv preprint arXiv:2503.20314"},{"key":"8_CR39","unstructured":"Wang, B., Yue, Z., Zhang, F., Chen, S., Bi, L., Zhang, J., Song, X., Chan, K.Y., Pan, J., Wu, W., Zhou, M., Lin, W., Pan, K., Zhang, S., Jia, L., Hu, W., Zhao, W., Zhang, H.: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning (2025). https:\/\/arxiv.org\/abs\/2505.07538"},{"issue":"5","key":"8_CR40","doi-asserted-by":"publisher","first-page":"3059","DOI":"10.1007\/s11263-024-02295-1","volume":"133","author":"Y Wang","year":"2025","unstructured":"Wang, Y., Chen, X., Ma, X., Zhou, S., Huang, Z., Wang, Y., Yang, C., He, Y., Yu, J., Yang, P., et al.: Lavie: high-quality video generation with cascaded latent diffusion models. Int. J. Comput. Vision 133(5), 3059\u20133078 (2025)","journal-title":"Int. J. Comput. Vision"},{"key":"8_CR41","unstructured":"Xue, Z., Wu, J., Gao, Y., Kong, F., Zhu, L., Chen, M., Liu, Z., Liu, W., Guo, Q., Huang, W., et\u00a0al.: Dancegrpo: Unleashing Grpo on Visual Generation (2025). arXiv preprint arXiv:2505.07818"},{"key":"8_CR42","unstructured":"Xue, Z., Zhang, J., Hu, T., He, H., Chen, Y., Cai, Y., Wang, Y., Wang, C., Liu, Y., Li, X., Tao, D.: Ultravideo: High-quality UHD Video Dataset with Comprehensive Captions (2025). arXiv preprint arXiv:2506.13691"},{"key":"8_CR43","unstructured":"Yan, W., Zhang, Y., Abbeel, P., Srinivas, A.: Videogpt: Video Generation Using VQ-VAE and Transformers (2021). arXiv:2104.10157 arXiv preprint"},{"key":"8_CR44","unstructured":"Yu, K., Zhang, T., Gong, Y.: Nonlinear learning using local coordinate coding. Adv. Neural. Inf. Process. Syst. 22, (2009)"},{"key":"8_CR45","unstructured":"Zhang, S., Kawaguchi, K., Yao, A.: Deep regression representation learning with topology. In: International Conference on Machine Learning (ICML), (2024)"},{"key":"8_CR46","unstructured":"Zhang, S., Yan, Y., Yao, A.: Improving Deep Regression with Tightness. ICLR (2025)"},{"key":"8_CR47","unstructured":"Zhang, S., Yang, L., Mi, M.B., Zheng, X., Yao, A.: Improving Deep Regression with Ordinal Entropy. ICLR (2023)"},{"key":"8_CR48","unstructured":"Zhao, Y., Joshi, R., Liu, T., Khalman, M., Saleh, M., Liu, P.J.: Slic-hf: Sequence Likelihood Calibration with Human Feedback (2023). arXiv preprint arXiv:2305.10425"},{"key":"8_CR49","unstructured":"Zheng, Z., Peng, X., Yang, T., Shen, C., Li, S., Liu, H., Zhou, Y., Li, T., You, Y.: Open-sora: Democratizing Efficient Video Production for All (2024). arXiv preprint arXiv:2412.20404"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37314-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:50:44Z","timestamp":1789462244000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37314-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373137","9783032373144"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37314-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"16 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}