{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:22:05Z","timestamp":1789118525213,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":64,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371669","type":"print"},{"value":"9783032371676","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\/978-3-032-37167-6_10","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:53:34Z","timestamp":1789116814000},"page":"170-189","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["LatSearch: Latent Reward-Guided Search for\u00a0Faster Inference-Time Scaling in\u00a0Video Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7135-1946","authenticated-orcid":false,"given":"Zengqun","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9724-2510","authenticated-orcid":false,"given":"Ziquan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9128-1775","authenticated-orcid":false,"given":"Yu","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8156-2299","authenticated-orcid":false,"given":"Shaogang","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7911-7564","authenticated-orcid":false,"given":"Zhensong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3381-6685","authenticated-orcid":false,"given":"Jifei","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3709-6216","authenticated-orcid":false,"given":"Jiankang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3913-4738","authenticated-orcid":false,"given":"Ioannis","family":"Patras","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"10_CR1","unstructured":"Agarwal, N., et al.: Cosmos world foundation model platform for physical AI. arXiv preprint arXiv:2501.03575 (2025)"},{"key":"10_CR2","unstructured":"Ban, Y., Wang, R., Zhou, T., Gong, B., Hsieh, C.J., Cheng, M.: The crystal ball hypothesis in diffusion models: anticipating object positions from initial noise. In: ICLR (2025)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Bao, F., et al.: All are worth words: a vit backbone for diffusion models. In: CVPR, pp. 22669\u201322679 (2023)","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Bhagat, S., Uppal, S., Yin, Z., Lim, N.: Disentangling multiple features in video sequences using gaussian processes in variational autoencoders. In: ECCV, pp. 102\u2013117. Springer (2020)","DOI":"10.1007\/978-3-030-58592-1_7"},{"key":"10_CR5","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Brooks, T., et al.: Generating long videos of dynamic scenes. In: NeurIPS, vol. 35, pp. 31769\u201331781 (2022)","DOI":"10.52202\/068431-2303"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Burgert, R., et al.: Go-with-the-flow: motion-controllable video diffusion models using real-time warped noise. In: CVPR, pp. 13\u201323 (2025)","DOI":"10.1109\/CVPR52734.2025.00011"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10_CR9","unstructured":"Chang, P., Tang, J., Gross, M., Azevedo, V.C.: How i warped your noise: a temporally-correlated noise prior for diffusion models. In: ICLR (2024)"},{"key":"10_CR10","unstructured":"Chen, H., et al.: Videocrafter1: open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Gentron: diffusion transformers for image and video generation. In: CVPR, pp. 6441\u20136451 (2024)","DOI":"10.1109\/CVPR52733.2024.00616"},{"key":"10_CR12","unstructured":"Chen, W., et al.: Control-a-video: controllable text-to-video diffusion models with motion prior and reward feedback learning. arXiv preprint arXiv:2305.13840 (2023)"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Dalal, K., et al.: One-minute video generation with test-time training. In: CVPR, pp. 17702\u201317711 (2025)","DOI":"10.1109\/CVPR52734.2025.01649"},{"key":"10_CR14","unstructured":"Deng, H., et al.: Autoregressive video generation without vector quantization. arXiv preprint arXiv:2412.14169 (2024)"},{"key":"10_CR15","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS, vol. 34, pp. 8780\u20138794 (2021)"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Ding, Z., et al.: Dollar: few-step video generation via distillation and latent reward optimization. arXiv preprint arXiv:2412.15689 (2024)","DOI":"10.1109\/ICCV51701.2025.01669"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Doucet, A., De Freitas, N., Gordon, N.: An introduction to sequential monte carlo methods. In: Sequential Monte Carlo Methods in Practice, pp. 3\u201314. Springer (2001)","DOI":"10.1007\/978-1-4757-3437-9_1"},{"key":"10_CR18","unstructured":"Gu, Y., Mao, W., Shou, M.Z.: Long-context autoregressive video modeling with next-frame prediction. arXiv preprint arXiv:2503.19325 (2025)"},{"key":"10_CR19","unstructured":"Guo, Y., et al.: Animatediff: animate your personalized text-to-image diffusion models without specific tuning. In: ICLR (2024)"},{"key":"10_CR20","unstructured":"He, H., et al.: Scaling image and video generation via test-time evolutionary search. arXiv preprint arXiv:2505.17618 (2025)"},{"key":"10_CR21","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS, vol. 30 (2017)"},{"key":"10_CR22","unstructured":"Hiranaka, A., et al.: Hero: human-feedback efficient reinforcement learning for online diffusion model finetuning. In: ICLR (2024)"},{"key":"10_CR23","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"10_CR24","unstructured":"Hsieh, J.T., Liu, B., Huang, D.A., Fei-Fei, L.F., Niebles, J.C.: Learning to decompose and disentangle representations for video prediction. In: NeurIPS, vol. 31 (2018)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Kara, O., Kurtkaya, B., Yesiltepe, H., Rehg, J.M., Yanardag, P.: Rave: randomized noise shuffling for fast and consistent video editing with diffusion models. In: CVPR, pp. 6507\u20136516 (2024)","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"10_CR26","doi-asserted-by":"crossref","unstructured":"Karras, J., Holynski, A., Wang, T.C., Kemelmacher-Shlizerman, I.: Dreampose: fashion image-to-video synthesis via stable diffusion. In: ICCV, pp. 22623\u201322633 (2023)","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"10_CR27","unstructured":"Kim, K., Kim, S.: Model already knows the best noise: Bayesian active noise selection via attention in video diffusion model. arXiv preprint arXiv:2505.17561 (2025)"},{"key":"10_CR28","unstructured":"Kong, W., et al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"10_CR29","unstructured":"Liao, X., Wei, W., Qu, X., Cheng, Y.: Step-level reward for free in RL-based T2I diffusion model fine-tuning. arXiv preprint arXiv:2505.19196 (2025)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Liu, F., Wang, H., Cai, Y., Zhang, K., Zhan, X., Duan, Y.: Video-T1: test-time scaling for video generation. arXiv preprint arXiv:2503.18942 (2025)","DOI":"10.1109\/ICCV51701.2025.01735"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Improving video generation with human feedback. In: NeurIPS (2025)","DOI":"10.52202\/085713-2750"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. Mach. Intell. Res. 1\u201322 (2025)","DOI":"10.1007\/s11633-025-1562-4"},{"key":"10_CR33","unstructured":"Luo, Y., et al.: Enhance-a-video: better generated video for free. arXiv preprint arXiv:2502.07508 (2025)"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Ma, N., et al.: Scaling inference time compute for diffusion models. In: CVPR, pp. 2523\u20132534 (2025)","DOI":"10.1109\/CVPR52734.2025.00241"},{"key":"10_CR35","unstructured":"Ma, Y., et al.: Tuning-free long video generation via global-local collaborative diffusion. arXiv preprint arXiv:2501.05484 (2025)"},{"key":"10_CR36","doi-asserted-by":"crossref","unstructured":"Nam, H., Kim, J., Lee, D., Ye, J.C.: Optical-flow guided prompt optimization for coherent video generation. In: CVPR, pp. 7837\u20137846 (2025)","DOI":"10.1109\/CVPR52734.2025.00734"},{"key":"10_CR37","doi-asserted-by":"crossref","unstructured":"Oshima, Y., Suzuki, M., Matsuo, Y., Furuta, H.: Inference-time text-to-video alignment with diffusion latent beam search. In: NeurIPS (2025)","DOI":"10.52202\/085713-0445"},{"key":"10_CR38","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: NeurIPS, vol. 35, pp. 27730\u201327744 (2022)","DOI":"10.52202\/068431-2011"},{"key":"10_CR39","doi-asserted-by":"crossref","unstructured":"Ouyang, W., et al.: Tokensgen: harnessing condensed tokens for long video generation. arXiv preprint arXiv:2507.15728 (2025)","DOI":"10.1109\/ICCV51701.2025.01691"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"10_CR41","doi-asserted-by":"crossref","unstructured":"Peruzzo, E., Xu, D., Xu, X., Shi, H., Sebe, N.: Ragme: retrieval augmented video generation for enhanced motion realism. In: ICMR, pp. 1081\u20131090 (2025)","DOI":"10.1145\/3731715.3733417"},{"key":"10_CR42","unstructured":"Qi, Z., Bai, L., Xiong, H., Xie, Z.: Not all noises are created equally: diffusion noise selection and optimization. arXiv preprint arXiv:2407.14041 (2024)"},{"key":"10_CR43","unstructured":"Qiu, H., et al.: Freenoise: tuning-free longer video diffusion via noise rescheduling. In: ICLR (2023)"},{"key":"10_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"key":"10_CR45","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: NeurIPS, vol. 29 (2016)"},{"key":"10_CR46","unstructured":"Singhal, R., et al.: A general framework for inference-time scaling and steering of diffusion models. arXiv preprint arXiv:2501.06848 (2025)"},{"key":"10_CR47","doi-asserted-by":"crossref","unstructured":"Skorokhodov, I., Tulyakov, S., Elhoseiny, M.: Stylegan-v: a continuous video generator with the price, image quality and perks of stylegan2. In: CVPR, pp. 3626\u20133636 (2022)","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"10_CR48","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"10_CR49","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 (2020)"},{"key":"10_CR50","unstructured":"Sun, Y., et al.: Swiftvideo: a unified framework for few-step video generation through trajectory-distribution alignment. arXiv preprint arXiv:2508.06082 (2025)"},{"key":"10_CR51","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"10_CR52","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"key":"10_CR53","unstructured":"Wang, P., et al.: Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution. arXiv preprint arXiv:2409.12191 (2024)"},{"key":"10_CR54","doi-asserted-by":"crossref","unstructured":"Wu, T., Si, C., Jiang, Y., Huang, Z., Liu, Z.: Freeinit: bridging initialization gap in video diffusion models. In: ECCV, pp. 378\u2013394 (2024)","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"10_CR55","doi-asserted-by":"crossref","unstructured":"Xiao, Z., Zhou, Y., Yang, S., Pan, X.: Video diffusion models are training-free motion interpreter and controller. In: NeurIPS, vol. 37, pp. 76115\u201376138 (2024)","DOI":"10.52202\/079017-2423"},{"key":"10_CR56","unstructured":"Yang, H., et al.: Scalingnoise: scaling inference-time search for generating infinite videos. arXiv preprint arXiv:2503.16400 (2025)"},{"key":"10_CR57","unstructured":"Yang, Z., et al.: Cogvideox: text-to-video diffusion models with an expert transformer. In: ICLR (2024)"},{"key":"10_CR58","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Instructvideo: instructing video diffusion models with human feedback. In: CVPR, pp. 6463\u20136474 (2024)","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"10_CR59","unstructured":"Yuan, Y., Guo, Y., Wang, C., Zhang, W., Xu, H., Zhang, L.: Freqprior: improving video diffusion models with frequency filtering gaussian noise. In: ICLR (2025)"},{"key":"10_CR60","unstructured":"Zhang, X., Duan, Z., Gong, D., Liu, L.: Training-free motion-guided video generation with enhanced temporal consistency using motion consistency loss. arXiv preprint arXiv:2501.07563 (2025)"},{"key":"10_CR61","doi-asserted-by":"crossref","unstructured":"Zhao, W., Bai, L., Rao, Y., Zhou, J., Lu, J.: Unipc: a unified predictor-corrector framework for fast sampling of diffusion models. In: NeurIPS, vol. 36, pp. 49842\u201349869 (2023)","DOI":"10.52202\/075280-2170"},{"key":"10_CR62","unstructured":"Zheng, D., et al.: Vbench-2.0: advancing video generation benchmark suite for intrinsic faithfulness. arXiv preprint arXiv:2503.21755 (2025)"},{"key":"10_CR63","unstructured":"Zhou, Z., et al.: Golden noise for diffusion models: a learning framework. arXiv preprint arXiv:2411.09502 (2024)"},{"key":"10_CR64","unstructured":"Zhu, B., et al.: Aligning anime video generation with human feedback. arXiv preprint arXiv:2504.10044 (2025)"}],"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\/978-3-032-37167-6_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:53:59Z","timestamp":1789116839000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37167-6_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371669","9783032371676"],"references-count":64,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37167-6_10","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":"12 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"}}]}}