{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T03:17:21Z","timestamp":1791170241014,"version":"4.1.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032369680","type":"print"},{"value":"9783032369697","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\/978-3-032-36969-7_23","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:21:32Z","timestamp":1789251692000},"page":"419-435","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Rethinking Reward Signals in\u00a0Video GRPO: When Scores Become Targets"],"prefix":"10.1007","author":[{"given":"Rui","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanzhi","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziqi","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibing","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"23_CR1","unstructured":"Assran, M., et al.: V-JEPA 2: self-supervised video models enable understanding, prediction and planning. arXiv preprint arXiv:2506.09985 (2025)"},{"key":"23_CR2","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"23_CR3","unstructured":"Christiano, P.F., Leike, J., Brown, T., Martic, M., Legg, S., Amodei, D.: Deep reinforcement learning from human preferences. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"23_CR4","unstructured":"Fang, X., Ma, L., Chen, Z., Zhou, M., Qi, G.J.: InfLVG: reinforce inference-time consistent long video generation with GRPO. arXiv preprint arXiv:2505.17574 (2025)"},{"key":"23_CR5","first-page":"26183","volume":"34","author":"Y Fang","year":"2021","unstructured":"Fang, Y., et al.: You only look at one sequence: rethinking transformer in vision through object detection. Adv. Neural. Inf. Process. Syst. 34, 26183\u201326197 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR6","unstructured":"Furuta, H., et al.: Improving dynamic object interactions in text-to-video generation with ai feedback. arXiv preprint arXiv:2412.02617 (2024)"},{"key":"23_CR7","first-page":"1457","volume":"5","author":"PO Hoyer","year":"2004","unstructured":"Hoyer, P.O.: Non-negative matrix factorization with sparseness constraints. J. Mach. Learn. Res. 5, 1457\u20131469 (2004)","journal-title":"J. Mach. Learn. Res."},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Hu, P., Xiao, N., Li, F., Chen, Y., Huang, R.: A reinforcement learning-based automatic video editing method using pre-trained vision-language model. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 6441\u20136450 (2023)","DOI":"10.1145\/3581783.3611878"},{"key":"23_CR9","unstructured":"Huang, G., et al.: Exposure bias can alleviate itself via directional and frequency rectification in flow matching (2026). https:\/\/arxiv.org\/abs\/2606.28226"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Z., 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":"23_CR11","unstructured":"Karwowski, J., Hayman, O., Bai, X., Kiendlhofer, K., Griffin, C., Skalse, J.: Goodhart\u2019s law in reinforcement learning. arXiv preprint arXiv:2310.09144 (2023)"},{"key":"23_CR12","unstructured":"Kong, W., et\u00a0al.: HunyuanVideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Li, R., Liu, D.: Spatial-then-temporal self-supervised learning for video correspondence. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2279\u20132288 (2023)","DOI":"10.1109\/CVPR52729.2023.00226"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Lin, J., Yin, H., Ping, W., Molchanov, P., Shoeybi, M., Han, S.: Vila: On pre-training for visual language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26689\u201326699 (2024)","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Ling, X., et al.: VMBench: a benchmark for perception-aligned video motion generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13087\u201313098 (2025)","DOI":"10.1109\/ICCV51701.2025.01216"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: Flow-GRPO: training flow matching models via online RL. arXiv preprint arXiv:2505.05470 (2025)","DOI":"10.52202\/085713-1362"},{"key":"23_CR17","unstructured":"Liu, J., et\u00a0al.: Improving video generation with human feedback. arXiv preprint arXiv:2501.13918 (2025)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Y., Xu, Q., Wen, P., Dai, S., Huang, Q.: When the future becomes the past: taming temporal correspondence for self-supervised video representation learning. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 24033\u201324044 (2025)","DOI":"10.1109\/CVPR52734.2025.02238"},{"key":"23_CR19","unstructured":"Luo, Y., et al.: Enhance-a-Video: better generated video for free. arXiv preprint arXiv:2502.07508 (2025)"},{"issue":"3","key":"23_CR20","doi-asserted-by":"publisher","first-page":"808","DOI":"10.1016\/j.ejor.2018.05.064","volume":"271","author":"Q Mercier","year":"2018","unstructured":"Mercier, Q., Poirion, F., D\u00e9sid\u00e9ri, J.A.: A stochastic multiple gradient descent algorithm. Eur. J. Oper. Res. 271(3), 808\u2013817 (2018)","journal-title":"Eur. J. Oper. Res."},{"key":"23_CR21","unstructured":"Mroueh, Y.: Reinforcement learning with verifiable rewards: GRPO\u2019s effective loss, dynamics, and success amplification. arXiv preprint arXiv:2503.06639 (2025)"},{"key":"23_CR22","unstructured":"Prabhudesai, M., Mendonca, R., Qin, Z., Fragkiadaki, K., Pathak, D.: Video diffusion alignment via reward gradients. arXiv preprint arXiv:2407.08737 (2024)"},{"key":"23_CR23","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"23_CR24","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. arXiv preprint arXiv:1910.10683 (2020)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Rohaly, A.M., et al.: Video quality experts group: current results and future directions. In: Visual Communications and Image Processing, vol. 4067, pp. 742\u2013753. SPIE (2000)","DOI":"10.1117\/12.386632"},{"key":"23_CR26","doi-asserted-by":"publisher","first-page":"25278","DOI":"10.52202\/068431-1833","volume":"35","author":"C Schuhmann","year":"2022","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. Adv. Neural. Inf. Process. Syst. 35, 25278\u201325294 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR27","unstructured":"Shao, Z., et\u00a0al.: DeepSeekMath: pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)"},{"key":"23_CR28","unstructured":"Sun, S., Liang, X., Qu, B., Gao, W.: Content-rich AIGC video quality assessment via intricate text alignment and motion-aware consistency. arXiv preprint arXiv:2502.04076 (2025)"},{"key":"23_CR29","doi-asserted-by":"publisher","first-page":"10078","DOI":"10.52202\/068431-0732","volume":"35","author":"Z Tong","year":"2022","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: masked autoencoders are data-efficient learners for self-supervised video pre-training. Adv. Neural. Inf. Process. Syst. 35, 10078\u201310093 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR30","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"23_CR31","unstructured":"Wang, J., et\u00a0al.: TAGRPO: Boosting GRPO on image-to-video generation with direct trajectory alignment. arXiv preprint arXiv:2601.05729 (2026)"},{"key":"23_CR32","unstructured":"Wu, J., et\u00a0al.: RewardDance: reward scaling in visual generation. arXiv preprint arXiv:2509.08826 (2025)"},{"key":"23_CR33","unstructured":"Wu, X., et al.: Human preference score v2: a solid benchmark for evaluating human preferences of text-to-image synthesis. arXiv preprint arXiv:2306.09341 (2023)"},{"key":"23_CR34","unstructured":"Xu, J., et\u00a0al.: VisionReward: fine-grained multi-dimensional human preference learning for image and video generation. arXiv preprint arXiv:2412.21059 (2024)"},{"key":"23_CR35","unstructured":"Xue, Z., et\u00a0al.: DanceGRPO: unleashing GRPO on visual generation. arXiv preprint arXiv:2505.07818 (2025)"},{"key":"23_CR36","unstructured":"Yang, R., et al.: Rewards-in-Context: multi-objective alignment of foundation models with dynamic preference adjustment. arXiv preprint arXiv:2402.10207 (2024)"},{"key":"23_CR37","unstructured":"Yang, X., Tan, Z., Li, H.: IPO: iterative preference optimization for text-to-video generation. arXiv preprint arXiv:2502.02088 (2025)"},{"key":"23_CR38","first-page":"5824","volume":"33","author":"T Yu","year":"2020","unstructured":"Yu, T., Kumar, S., Gupta, A., Levine, S., Hausman, K., Finn, C.: Gradient surgery for multi-task learning. Adv. Neural. Inf. Process. Syst. 33, 5824\u20135836 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: InstructVideo: instructing video diffusion models with human feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6463\u20136474 (2024)","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"23_CR40","unstructured":"Zhang, Y.F., et\u00a0al.: R1-Reward: training multimodal reward model through stable reinforcement learning. arXiv preprint arXiv:2505.02835 (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\/978-3-032-36969-7_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:21:36Z","timestamp":1789251696000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-36969-7_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032369680","9783032369697"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-36969-7_23","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":"13 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"}}]}}